{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/ppo/papers/ran/1","list_of":"/method/ppo","method":"PPO","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not isolate this method inside it.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":2,"rows_per_page":100,"rows":[1,100],"of":139,"counts":{"archive_papers_tagged":949,"with_a_code_link":397,"where_syntology_ran_a_sample":139,"not_listed_spam_title":0,"listed":949,"listed_where_code_ran":139,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":114,"every_run_a_failure_of_syntologys_instrument":25,"listed_with_a_run_with_no_instrument_failure":114,"listed_every_run_a_failure_of_syntologys_instrument":25,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/ppo/papers/ran/1","prev":null,"next":"/method/ppo/papers/ran/2","papers":[{"paper":"/paper/tgdpo-harnessing-token-level-reward-guidance","slug":"tgdpo-harnessing-token-level-reward-guidance","title":"TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization","date":"2025-06-17","arxiv_id":"2506.14574","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dvlab-research/tgdpo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/autovla-a-vision-language-action-model-for","slug":"autovla-a-vision-language-action-model-for","title":"AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning","date":"2025-06-16","arxiv_id":"2506.13757","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ucla-mobility/AutoVLA"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-surprising-effectiveness-of-negative","slug":"the-surprising-effectiveness-of-negative","title":"The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning","date":"2025-06-02","arxiv_id":"2506.01347","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tianhongzxy/rlvr-decomposed"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/areal-a-large-scale-asynchronous","slug":"areal-a-large-scale-asynchronous","title":"AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning","date":"2025-05-30","arxiv_id":"2505.24298","n_code_links":1,"syntology":{"ran":10,"of":13,"n_ran_checked":10,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["inclusionai/areal"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/segment-policy-optimization-effective-segment","slug":"segment-policy-optimization-effective-segment","title":"Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models","date":"2025-05-29","arxiv_id":"2505.23564","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":7,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["aiframeresearch/spo"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/trajectory-bellman-residual-minimization-a","slug":"trajectory-bellman-residual-minimization-a","title":"Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning","date":"2025-05-21","arxiv_id":"2505.15311","n_code_links":0,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/reinforcement-learning-finetunes-small","slug":"reinforcement-learning-finetunes-small","title":"Reinforcement Learning Finetunes Small Subnetworks in Large Language Models","date":"2025-05-16","arxiv_id":"2505.11711","n_code_links":0,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/carl-learning-scalable-planning-policies-with","slug":"carl-learning-scalable-planning-policies-with","title":"CaRL: Learning Scalable Planning Policies with Simple Rewards","date":"2025-04-24","arxiv_id":"2504.17838","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["autonomousvision/CaRL"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-minimalist-approach-to-llm-reasoning-from","slug":"a-minimalist-approach-to-llm-reasoning-from","title":"A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce","date":"2025-04-15","arxiv_id":"2504.11343","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["rlhflow/minimal-rl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/concise-reasoning-via-reinforcement-learning","slug":"concise-reasoning-via-reinforcement-learning","title":"Concise Reasoning via Reinforcement Learning","date":"2025-04-07","arxiv_id":"2504.05185","n_code_links":1,"syntology":{"ran":12,"of":14,"n_ran_checked":11,"n_instrument":1,"unverified":2,"pointer_only":13,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ai-wand/concise-reasoning"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/end-to-end-driving-with-online-trajectory","slug":"end-to-end-driving-with-online-trajectory","title":"End-to-End Driving with Online Trajectory Evaluation via BEV World Model","date":"2025-04-02","arxiv_id":"2504.01941","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":7,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"7 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 7 samples that ran constructed an object rather than computing a result","official":{"repos":["liyingyanucas/wote"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":7,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/open-reasoner-zero-an-open-source-approach-to","slug":"open-reasoner-zero-an-open-source-approach-to","title":"Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model","date":"2025-03-31","arxiv_id":"2503.24290","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":1,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/uniocc-a-unified-benchmark-for-occupancy","slug":"uniocc-a-unified-benchmark-for-occupancy","title":"UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Driving","date":"2025-03-31","arxiv_id":"2503.24381","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["tasl-lab/uniocc"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/simlingo-vision-only-closed-loop-autonomous","slug":"simlingo-vision-only-closed-loop-autonomous","title":"SimLingo: Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignment","date":"2025-03-12","arxiv_id":"2503.09594","n_code_links":1,"syntology":{"ran":11,"of":14,"n_ran_checked":8,"n_instrument":3,"unverified":3,"pointer_only":0,"phrase":"11 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/reevaluating-policy-gradient-methods-for","slug":"reevaluating-policy-gradient-methods-for","title":"Reevaluating Policy Gradient Methods for Imperfect-Information Games","date":"2025-02-13","arxiv_id":"2502.08938","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["gabrfarina/exp-a-spiel","nathanlct/iig-rl-benchmark"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/on-the-emergence-of-thinking-in-llms-i","slug":"on-the-emergence-of-thinking-in-llms-i","title":"On the Emergence of Thinking in LLMs I: Searching for the Right Intuition","date":"2025-02-10","arxiv_id":"2502.06773","n_code_links":4,"syntology":{"ran":11,"of":13,"n_ran_checked":11,"n_instrument":0,"unverified":2,"pointer_only":9,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["GuanghaoYe/Emergence-of-Thinking"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/leapvad-a-leap-in-autonomous-driving-via","slug":"leapvad-a-leap-in-autonomous-driving-via","title":"LeapVAD: A Leap in Autonomous Driving via Cognitive Perception and Dual-Process Thinking","date":"2025-01-14","arxiv_id":"2501.08168","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":3,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/efficient-policy-adaptation-with-contrastive-1","slug":"efficient-policy-adaptation-with-contrastive-1","title":"Efficient Policy Adaptation with Contrastive Prompt Ensemble for Embodied Agents","date":"2024-12-16","arxiv_id":"2412.11484","n_code_links":0,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":null}},{"paper":"/paper/wisead-knowledge-augmented-end-to-end","slug":"wisead-knowledge-augmented-end-to-end","title":"WiseAD: Knowledge Augmented End-to-End Autonomous Driving with Vision-Language Model","date":"2024-12-13","arxiv_id":"2412.09951","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["wyddmw/WiseAD"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/hidden-biases-of-end-to-end-driving-datasets","slug":"hidden-biases-of-end-to-end-driving-datasets","title":"Hidden Biases of End-to-End Driving Datasets","date":"2024-12-12","arxiv_id":"2412.09602","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["autonomousvision/carla_garage"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-method-for-evaluating-hyperparameter","slug":"a-method-for-evaluating-hyperparameter","title":"A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning","date":"2024-12-10","arxiv_id":"2412.07165","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jadkins99/hyperparameter_sensitivity"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/cale-continuous-arcade-learning-environment","slug":"cale-continuous-arcade-learning-environment","title":"CALE: Continuous Arcade Learning Environment","date":"2024-10-31","arxiv_id":"2410.23810","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["farama-foundation/arcade-learning-environment"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/fast-best-of-n-decoding-via-speculative","slug":"fast-best-of-n-decoding-via-speculative","title":"Fast Best-of-N Decoding via Speculative Rejection","date":"2024-10-26","arxiv_id":"2410.20290","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":1,"n_instrument":3,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Zanette-Labs/SpeculativeRejection"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/unidrive-towards-universal-driving-perception","slug":"unidrive-towards-universal-driving-perception","title":"UniDrive: Towards Universal Driving Perception Across Camera Configurations","date":"2024-10-17","arxiv_id":"2410.13864","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":5,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ywyeli/unidrive"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/coevolving-with-the-other-you-fine-tuning-llm","slug":"coevolving-with-the-other-you-fine-tuning-llm","title":"Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning","date":"2024-10-08","arxiv_id":"2410.06101","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":6,"n_instrument":2,"unverified":3,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["Harry67Hu/CORY"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/vineppo-unlocking-rl-potential-for-llm","slug":"vineppo-unlocking-rl-potential-for-llm","title":"VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment","date":"2024-10-02","arxiv_id":"2410.01679","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":7,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["mcgill-nlp/vineppo"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/instruct-skillmix-a-powerful-pipeline-for-llm","slug":"instruct-skillmix-a-powerful-pipeline-for-llm","title":"Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning","date":"2024-08-27","arxiv_id":"2408.14774","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":6,"n_instrument":1,"unverified":1,"pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["princeton-pli/Instruct-SkillMix"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/simplifying-deep-temporal-difference-learning","slug":"simplifying-deep-temporal-difference-learning","title":"Simplifying Deep Temporal Difference Learning","date":"2024-07-05","arxiv_id":"2407.04811","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mttga/purejaxql"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/decoding-time-language-model-alignment-with","slug":"decoding-time-language-model-alignment-with","title":"Decoding-Time Language Model Alignment with Multiple Objectives","date":"2024-06-27","arxiv_id":"2406.18853","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["srzer/mod"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/unpacking-dpo-and-ppo-disentangling-best","slug":"unpacking-dpo-and-ppo-disentangling-best","title":"Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback","date":"2024-06-13","arxiv_id":"2406.09279","n_code_links":2,"syntology":{"ran":15,"of":19,"n_ran_checked":8,"n_instrument":7,"unverified":4,"pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified","official":{"repos":["allenai/open-instruct","hamishivi/easylm"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/flow-of-reasoning-efficient-training-of-llm","slug":"flow-of-reasoning-efficient-training-of-llm","title":"Flow of Reasoning:Training LLMs for Divergent Problem Solving with Minimal Examples","date":"2024-06-09","arxiv_id":"2406.05673","n_code_links":1,"syntology":{"ran":11,"of":15,"n_ran_checked":11,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["yu-fangxu/for"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/bench2drive-towards-multi-ability","slug":"bench2drive-towards-multi-ability","title":"Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving","date":"2024-06-06","arxiv_id":"2406.03877","n_code_links":4,"syntology":{"ran":13,"of":17,"n_ran_checked":10,"n_instrument":3,"unverified":4,"pointer_only":17,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["Thinklab-SJTU/Bench2Drive","autonomousvision/carla_garage","thinklab-sjtu/bench2drivezoo"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/hackatari-atari-learning-environments-for","slug":"hackatari-atari-learning-environments-for","title":"HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learning","date":"2024-06-06","arxiv_id":"2406.03997","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["k4ntz/HackAtari"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/agile-a-novel-framework-of-llm-agents","slug":"agile-a-novel-framework-of-llm-agents","title":"AGILE: A Novel Reinforcement Learning Framework of LLM Agents","date":"2024-05-23","arxiv_id":"2405.14751","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["bytarnish/agile"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/chatscene-knowledge-enabled-safety-critical","slug":"chatscene-knowledge-enabled-safety-critical","title":"ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles","date":"2024-05-22","arxiv_id":"2405.14062","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["javyduck/ChatScene"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/value-augmented-sampling-for-language-model","slug":"value-augmented-sampling-for-language-model","title":"Value Augmented Sampling for Language Model Alignment and Personalization","date":"2024-05-10","arxiv_id":"2405.06639","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["idanshen/Value-Augmented-Sampling"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/d2po-discriminator-guided-dpo-with-response","slug":"d2po-discriminator-guided-dpo-with-response","title":"D2PO: Discriminator-Guided DPO with Response Evaluation Models","date":"2024-05-02","arxiv_id":"2405.01511","n_code_links":1,"syntology":{"ran":11,"of":13,"n_ran_checked":11,"n_instrument":0,"unverified":2,"pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["PrasannS/d2po"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/no-representation-no-trust-connecting","slug":"no-representation-no-trust-connecting","title":"No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO","date":"2024-05-01","arxiv_id":"2405.00662","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":5,"n_instrument":1,"unverified":2,"pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["claire-labo/no-representation-no-trust"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/dpo-meets-ppo-reinforced-token-optimization","slug":"dpo-meets-ppo-reinforced-token-optimization","title":"DPO Meets PPO: Reinforced Token Optimization for RLHF","date":"2024-04-29","arxiv_id":"2404.18922","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":3,"n_instrument":1,"unverified":2,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zkshan2002/rto"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/rebel-reinforcement-learning-via-regressing","slug":"rebel-reinforcement-learning-via-regressing","title":"REBEL: Reinforcement Learning via Regressing Relative Rewards","date":"2024-04-25","arxiv_id":"2404.16767","n_code_links":3,"syntology":{"ran":16,"of":20,"n_ran_checked":12,"n_instrument":4,"unverified":4,"pointer_only":6,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","official":{"repos":["Owen-Oertell/rlcm","zhaolingao/rebel"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/addressing-loss-of-plasticity-and","slug":"addressing-loss-of-plasticity-and","title":"Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning","date":"2024-03-31","arxiv_id":"2404.00781","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["mohmdelsayed/upgd"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/craftax-a-lightning-fast-benchmark-for-open","slug":"craftax-a-lightning-fast-benchmark-for-open","title":"Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning","date":"2024-02-26","arxiv_id":"2402.16801","n_code_links":1,"syntology":{"ran":2,"of":16,"n_ran_checked":2,"n_instrument":0,"unverified":14,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 14 unverified","official":{"repos":["michaeltmatthews/craftax"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":14,"ran_from_kinds":["official"]}}},{"paper":"/paper/vadv2-end-to-end-vectorized-autonomous","slug":"vadv2-end-to-end-vectorized-autonomous","title":"VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning","date":"2024-02-20","arxiv_id":"2402.13243","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hustvl/vad"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["community","official"]}}},{"paper":"/paper/entropy-regularized-token-level-policy","slug":"entropy-regularized-token-level-policy","title":"Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement","date":"2024-02-09","arxiv_id":"2402.06700","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":3,"n_instrument":3,"unverified":3,"pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["morning9393/etpo"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-to-generate-explainable-stock","slug":"learning-to-generate-explainable-stock","title":"Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Models","date":"2024-02-06","arxiv_id":"2402.03659","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["koa-fin/sep"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/compound-returns-reduce-variance-in","slug":"compound-returns-reduce-variance-in","title":"Averaging $n$-step Returns Reduces Variance in Reinforcement Learning","date":"2024-02-06","arxiv_id":"2402.03903","n_code_links":0,"syntology":{"ran":5,"of":8,"n_ran_checked":4,"n_instrument":1,"unverified":3,"pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/deepseekmath-pushing-the-limits-of","slug":"deepseekmath-pushing-the-limits-of","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","date":"2024-02-05","arxiv_id":"2402.03300","n_code_links":5,"syntology":{"ran":14,"of":24,"n_ran_checked":10,"n_instrument":4,"unverified":10,"pointer_only":3,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified","official":{"repos":["deepseek-ai/deepseek-math"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/true-knowledge-comes-from-practice-aligning","slug":"true-knowledge-comes-from-practice-aligning","title":"True Knowledge Comes from Practice: Aligning LLMs with Embodied Environments via Reinforcement Learning","date":"2024-01-25","arxiv_id":"2401.14151","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["weihaotan/twosome"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/linear-alignment-a-closed-form-solution-for","slug":"linear-alignment-a-closed-form-solution-for","title":"Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback","date":"2024-01-21","arxiv_id":"2401.11458","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["wizardcoast/linear_alignment"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/langprop-a-code-optimization-framework-using","slug":"langprop-a-code-optimization-framework-using","title":"LangProp: A code optimization framework using Large Language Models applied to driving","date":"2024-01-18","arxiv_id":"2401.10314","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["shuishida/langprop"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/reft-reasoning-with-reinforced-fine-tuning","slug":"reft-reasoning-with-reinforced-fine-tuning","title":"ReFT: Reasoning with Reinforced Fine-Tuning","date":"2024-01-17","arxiv_id":"2401.08967","n_code_links":1,"syntology":{"ran":5,"of":14,"n_ran_checked":5,"n_instrument":0,"unverified":9,"pointer_only":13,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","official":{"repos":["lqtrung1998/mwp_reft"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":"/paper/mapo-advancing-multilingual-reasoning-through","slug":"mapo-advancing-multilingual-reasoning-through","title":"MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization","date":"2024-01-12","arxiv_id":"2401.06838","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":5,"n_instrument":1,"unverified":4,"pointer_only":10,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["njunlp/mapo"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/some-things-are-more-cringe-than-others","slug":"some-things-are-more-cringe-than-others","title":"Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Loss","date":"2023-12-27","arxiv_id":"2312.16682","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/gradient-informed-proximal-policy-1","slug":"gradient-informed-proximal-policy-1","title":"Gradient Informed Proximal Policy Optimization","date":"2023-12-14","arxiv_id":"2312.08710","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["sonsang/gippo"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/drivemlm-aligning-multi-modal-large-language","slug":"drivemlm-aligning-multi-modal-large-language","title":"DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Driving","date":"2023-12-14","arxiv_id":"2312.09245","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["opengvlab/drivemlm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/black-box-prompt-optimization-aligning-large","slug":"black-box-prompt-optimization-aligning-large","title":"Black-Box Prompt Optimization: Aligning Large Language Models without Model Training","date":"2023-11-07","arxiv_id":"2311.04155","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["thu-coai/bpo"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/reward-scale-robustness-for-proximal-policy","slug":"reward-scale-robustness-for-proximal-policy","title":"Reward Scale Robustness for Proximal Policy Optimization via DreamerV3 Tricks","date":"2023-10-26","arxiv_id":"2310.17805","n_code_links":0,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/safe-navigation-training-autonomous-vehicles","slug":"safe-navigation-training-autonomous-vehicles","title":"Safe Navigation: Training Autonomous Vehicles using Deep Reinforcement Learning in CARLA","date":"2023-10-23","arxiv_id":"2311.10735","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["tejas-deo/safe-navigation-training-autonomous-vehicles-using-deep-reinforcement-learning-in-carla"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/remax-a-simple-effective-and-efficient-method","slug":"remax-a-simple-effective-and-efficient-method","title":"ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models","date":"2023-10-16","arxiv_id":"2310.10505","n_code_links":3,"syntology":{"ran":11,"of":13,"n_ran_checked":10,"n_instrument":1,"unverified":2,"pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["liziniu/ReMax"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/dsac-t-distributional-soft-actor-critic-with","slug":"dsac-t-distributional-soft-actor-critic-with","title":"Distributional Soft Actor-Critic with Three Refinements","date":"2023-10-09","arxiv_id":"2310.05858","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jingliang-duan/dsac-t","jingliang-duan/dsac-v2"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/reinforcement-learning-in-the-era-of-llms","slug":"reinforcement-learning-in-the-era-of-llms","title":"Reinforcement Learning in the Era of LLMs: What is Essential? What is needed? An RL Perspective on RLHF, Prompting, and Beyond","date":"2023-10-09","arxiv_id":"2310.06147","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/reward-model-ensembles-help-mitigate","slug":"reward-model-ensembles-help-mitigate","title":"Reward Model Ensembles Help Mitigate Overoptimization","date":"2023-10-04","arxiv_id":"2310.02743","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":0,"n_instrument":5,"unverified":0,"pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tlc4418/llm_optimization"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/cleanba-a-reproducible-and-efficient","slug":"cleanba-a-reproducible-and-efficient","title":"Cleanba: A Reproducible and Efficient Distributed Reinforcement Learning Platform","date":"2023-09-29","arxiv_id":"2310.00036","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":4,"n_instrument":0,"unverified":4,"pointer_only":8,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["vwxyzjn/cleanba"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/exploring-the-impact-of-low-rank-adaptation","slug":"exploring-the-impact-of-low-rank-adaptation","title":"Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of RLHF","date":"2023-09-16","arxiv_id":"2309.09055","n_code_links":1,"syntology":{"ran":12,"of":13,"n_ran_checked":12,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["simengsun/alpaca_farm_lora"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/parallel-q-learning-scaling-off-policy","slug":"parallel-q-learning-scaling-off-policy","title":"Parallel $Q$-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation","date":"2023-07-24","arxiv_id":"2307.12983","n_code_links":0,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/llama-2-open-foundation-and-fine-tuned-chat","slug":"llama-2-open-foundation-and-fine-tuned-chat","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","date":"2023-07-18","arxiv_id":"2307.09288","n_code_links":19,"syntology":{"ran":33,"of":52,"n_ran_checked":22,"n_instrument":11,"unverified":19,"pointer_only":20,"phrase":"33 ran (of which 7 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 1 violated, 20 with no contract checked; 11 where Syntology's instrument failed) · 19 unverified","official":{"repos":["facebookresearch/llama"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/hidden-biases-of-end-to-end-driving-models","slug":"hidden-biases-of-end-to-end-driving-models","title":"Hidden Biases of End-to-End Driving Models","date":"2023-06-13","arxiv_id":"2306.07957","n_code_links":1,"syntology":{"ran":13,"of":17,"n_ran_checked":10,"n_instrument":3,"unverified":4,"pointer_only":0,"phrase":"13 ran (of which 10 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["autonomousvision/carla_garage"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":10,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/fine-tuning-language-models-with-advantage","slug":"fine-tuning-language-models-with-advantage","title":"Fine-Tuning Language Models with Advantage-Induced Policy Alignment","date":"2023-06-04","arxiv_id":"2306.02231","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["microsoft/rlhf-apa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/normalization-enhances-generalization-in","slug":"normalization-enhances-generalization-in","title":"Normalization Enhances Generalization in Visual Reinforcement Learning","date":"2023-06-01","arxiv_id":"2306.00656","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["lilucse/Normalization-Enhances-Generalization-in-Visual-Reinforcement-Learning"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/think-twice-before-driving-towards-scalable","slug":"think-twice-before-driving-towards-scalable","title":"Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving","date":"2023-05-10","arxiv_id":"2305.06242","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["opendrivelab/thinktwice"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/reducing-the-cost-of-cycle-time-tuning-for","slug":"reducing-the-cost-of-cycle-time-tuning-for","title":"Reducing the Cost of Cycle-Time Tuning for Real-World Policy Optimization","date":"2023-05-09","arxiv_id":"2305.05760","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["homayoonfarrahi/cycle-time-study"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/local-optimization-achieves-global-optimality","slug":"local-optimization-achieves-global-optimality","title":"Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning","date":"2023-05-08","arxiv_id":"2305.04819","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zhaoyl18/ratio_game"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/rrhf-rank-responses-to-align-language-models","slug":"rrhf-rank-responses-to-align-language-models","title":"RRHF: Rank Responses to Align Language Models with Human Feedback without tears","date":"2023-04-11","arxiv_id":"2304.05302","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ganjinzero/rrhf"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/autorl-hyperparameter-landscapes","slug":"autorl-hyperparameter-landscapes","title":"AutoRL Hyperparameter Landscapes","date":"2023-04-05","arxiv_id":"2304.02396","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["automl/autorl-landscape"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/behavior-proximal-policy-optimization","slug":"behavior-proximal-policy-optimization","title":"Behavior Proximal Policy Optimization","date":"2023-02-22","arxiv_id":"2302.11312","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dragon-zhuang/bppo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/dynamic-simplex-balancing-safety-and","slug":"dynamic-simplex-balancing-safety-and","title":"Dynamic Simplex: Balancing Safety and Performance in Autonomous Cyber Physical Systems","date":"2023-02-20","arxiv_id":"2302.09750","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["BaitingLuo/Dynamic_Simplex"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/sample-dropout-a-simple-yet-effective","slug":"sample-dropout-a-simple-yet-effective","title":"Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization","date":"2023-02-05","arxiv_id":"2302.02299","n_code_links":1,"syntology":{"ran":6,"of":12,"n_ran_checked":5,"n_instrument":1,"unverified":6,"pointer_only":12,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["linzichuan/sdpo"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/robust-policy-optimization-in-deep","slug":"robust-policy-optimization-in-deep","title":"Robust Policy Optimization in Deep Reinforcement Learning","date":"2022-12-14","arxiv_id":"2212.07536","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["vwxyzjn/cleanrl"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":"/paper/analyzing-infrastructure-lidar-placement-with","slug":"analyzing-infrastructure-lidar-placement-with","title":"Analyzing Infrastructure LiDAR Placement with Realistic LiDAR Simulation Library","date":"2022-11-29","arxiv_id":"2211.15975","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["pjlab-adg/lidarsimlib-and-placement-evaluation","pjlab-adg/pcsim"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/plant-explainable-planning-transformers-via","slug":"plant-explainable-planning-transformers-via","title":"PlanT: Explainable Planning Transformers via Object-Level Representations","date":"2022-10-25","arxiv_id":"2210.14222","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["autonomousvision/plant"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/model-based-imitation-learning-for-urban","slug":"model-based-imitation-learning-for-urban","title":"Model-Based Imitation Learning for Urban Driving","date":"2022-10-14","arxiv_id":"2210.07729","n_code_links":1,"syntology":{"ran":21,"of":23,"n_ran_checked":13,"n_instrument":8,"unverified":2,"pointer_only":0,"phrase":"21 ran (of which 13 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified","official":{"repos":["wayveai/mile"],"state":"official (archive's flag): 21 ran","n_ran":21,"n_constructed":13,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/real-time-reinforcement-learning-for-vision","slug":"real-time-reinforcement-learning-for-vision","title":"Real-Time Reinforcement Learning for Vision-Based Robotics Utilizing Local and Remote Computers","date":"2022-10-05","arxiv_id":"2210.02317","n_code_links":2,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["rlai-lab/relod","rlai-lab/remote-onboard-agent"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-to-generalize-with-object-centric","slug":"learning-to-generalize-with-object-centric","title":"Learning to Generalize with Object-centric Agents in the Open World Survival Game Crafter","date":"2022-08-05","arxiv_id":"2208.03374","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["astanic/crafter-ood"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/safety-enhanced-autonomous-driving-using-1","slug":"safety-enhanced-autonomous-driving-using-1","title":"Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer","date":"2022-07-28","arxiv_id":"2207.14024","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["opendilab/InterFuser"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/st-p3-end-to-end-vision-based-autonomous","slug":"st-p3-end-to-end-vision-based-autonomous","title":"ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning","date":"2022-07-15","arxiv_id":"2207.07601","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/automated-detection-of-label-errors-in","slug":"automated-detection-of-label-errors-in","title":"Automated Detection of Label Errors in Semantic Segmentation Datasets via Deep Learning and Uncertainty Quantification","date":"2022-07-13","arxiv_id":"2207.06104","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["mrcoee/automatic-label-error-detection"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/envpool-a-highly-parallel-reinforcement","slug":"envpool-a-highly-parallel-reinforcement","title":"EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine","date":"2022-06-21","arxiv_id":"2206.10558","n_code_links":3,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sail-sg/envpool"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["named_in_paper","official"]}}},{"paper":"/paper/a-unified-approach-to-reinforcement-learning","slug":"a-unified-approach-to-reinforcement-learning","title":"A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games","date":"2022-06-12","arxiv_id":"2206.05825","n_code_links":3,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 3 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["deepmind/open_spiel"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["named_in_paper"]}}},{"paper":"/paper/transfuser-imitation-with-transformer-based","slug":"transfuser-imitation-with-transformer-based","title":"TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving","date":"2022-05-31","arxiv_id":"2205.15997","n_code_links":3,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["autonomousvision/transfuser"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/efficient-reward-poisoning-attacks-on-online","slug":"efficient-reward-poisoning-attacks-on-online","title":"Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning","date":"2022-05-30","arxiv_id":"2205.14842","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yinglunxu/reward_poisoning_attack_drl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/quark-controllable-text-generation-with","slug":"quark-controllable-text-generation-with","title":"Quark: Controllable Text Generation with Reinforced Unlearning","date":"2022-05-26","arxiv_id":"2205.13636","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["gximinglu/quark"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/an-evaluation-study-of-intrinsic-motivation","slug":"an-evaluation-study-of-intrinsic-motivation","title":"An Evaluation Study of Intrinsic Motivation Techniques applied to Reinforcement Learning over Hard Exploration Environments","date":"2022-05-23","arxiv_id":"2205.11184","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["aklein1995/intrinsic_motivation_techniques_study"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/cliff-diving-exploring-reward-surfaces-in","slug":"cliff-diving-exploring-reward-surfaces-in","title":"Cliff Diving: Exploring Reward Surfaces in Reinforcement Learning Environments","date":"2022-05-14","arxiv_id":"2205.07015","n_code_links":0,"syntology":{"ran":2,"of":4,"n_ran_checked":1,"n_instrument":1,"unverified":2,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/king-generating-safety-critical-driving","slug":"king-generating-safety-critical-driving","title":"KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients","date":"2022-04-28","arxiv_id":"2204.13683","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["autonomousvision/king"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-from-all-vehicles","slug":"learning-from-all-vehicles","title":"Learning from All Vehicles","date":"2022-03-22","arxiv_id":"2203.11934","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["dotchen/LAV"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/v2x-vit-vehicle-to-everything-cooperative","slug":"v2x-vit-vehicle-to-everything-cooperative","title":"V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer","date":"2022-03-20","arxiv_id":"2203.10638","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["DerrickXuNu/v2x-vit"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/panoflow-learning-optical-flow-for-panoramic","slug":"panoflow-learning-optical-flow-for-panoramic","title":"PanoFlow: Learning 360° Optical Flow for Surrounding Temporal Understanding","date":"2022-02-27","arxiv_id":"2202.13388","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["masterhow/panoflow"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/cadre-a-cascade-deep-reinforcement-learning","slug":"cadre-a-cascade-deep-reinforcement-learning","title":"CADRE: A Cascade Deep Reinforcement Learning Framework for Vision-based Autonomous Urban Driving","date":"2022-02-17","arxiv_id":"2202.08557","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"8 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["BIT-MCS/Cadre"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":7,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-distilled-collaboration-graph-for","slug":"learning-distilled-collaboration-graph-for","title":"Learning Distilled Collaboration Graph for Multi-Agent Perception","date":"2021-11-01","arxiv_id":"2111.00643","n_code_links":2,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["ai4ce/DiscoNet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/object-aware-regularization-for-addressing","slug":"object-aware-regularization-for-addressing","title":"Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning","date":"2021-10-27","arxiv_id":"2110.14118","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["alinlab/oreo"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"24d7e40c72ee78ad0639df65b31ac0a25cbf88b6a933a4c4e8118cf05bbac6cc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}