{"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":"/task/reinforcement-learning-1/papers/15","list_of":"/task/reinforcement-learning-1","task":"Reinforcement Learning (RL)","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":15,"pages_in_order":152,"rows_per_page":100,"rows":[1401,1500],"of":15113,"counts":{"archive_papers_tagged":15113,"with_a_code_link":4749,"where_syntology_ran_a_sample":1416,"not_listed_spam_title":0,"listed":15113,"listed_where_code_ran":1416,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1186,"every_run_a_failure_of_syntologys_instrument":230,"listed_with_a_run_with_no_instrument_failure":1186,"listed_every_run_a_failure_of_syntologys_instrument":230,"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":"/task/reinforcement-learning-1","prev":"/task/reinforcement-learning-1/papers/14","next":"/task/reinforcement-learning-1/papers/16","papers":[{"url":"/paper/predictive-coding-for-decision-transformer","slug":"predictive-coding-for-decision-transformer","title":"Predictive Coding for Decision Transformer","date":"2024-10-04","arxiv_id":"2410.03408","repositories_listed":1,"syntology":null},{"url":"/paper/relic-a-recipe-for-64k-steps-of-in-context","slug":"relic-a-recipe-for-64k-steps-of-in-context","title":"ReLIC: A Recipe for 64k Steps of In-Context Reinforcement Learning for Embodied AI","date":"2024-10-03","arxiv_id":"2410.02751","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"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","sample_list":"/paper/relic-a-recipe-for-64k-steps-of-in-context#ran","syntology_url":"https://syntology.ai/paper/2410.02751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02751"}},"official":{"repos":["aielawady/relic"],"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"]}}},{"url":"/paper/adaptive-teachers-for-amortized-samplers","slug":"adaptive-teachers-for-amortized-samplers","title":"Adaptive teachers for amortized samplers","date":"2024-10-02","arxiv_id":"2410.01432","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":1,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adaptive-teachers-for-amortized-samplers#ran","syntology_url":"https://syntology.ai/paper/2410.01432","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01432"}},"official":{"repos":["alstn12088/adaptive-teacher"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_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","sample_list":"/paper/vineppo-unlocking-rl-potential-for-llm#ran","syntology_url":"https://syntology.ai/paper/2410.01679","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01679"}},"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"]}}},{"url":"/paper/scaling-offline-model-based-rl-via-jointly","slug":"scaling-offline-model-based-rl-via-jointly","title":"Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining","date":"2024-10-01","arxiv_id":"2410.00564","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":13,"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","sample_list":"/paper/scaling-offline-model-based-rl-via-jointly#ran","syntology_url":"https://syntology.ai/paper/2410.00564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.00564"}},"official":{"repos":["cjreinforce/jowa"],"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"]}}},{"url":"/paper/constrained-reinforcement-learning-for-safe","slug":"constrained-reinforcement-learning-for-safe","title":"Constrained Reinforcement Learning for Safe Heat Pump Control","date":"2024-09-29","arxiv_id":"2409.19716","repositories_listed":1,"syntology":null},{"url":"/paper/arlbench-flexible-and-efficient-benchmarking","slug":"arlbench-flexible-and-efficient-benchmarking","title":"ARLBench: Flexible and Efficient Benchmarking for Hyperparameter Optimization in Reinforcement Learning","date":"2024-09-27","arxiv_id":"2409.18827","repositories_listed":1,"syntology":null},{"url":"/paper/climate-adaptation-with-reinforcement","slug":"climate-adaptation-with-reinforcement","title":"Climate Adaptation with Reinforcement Learning: Experiments with Flooding and Transportation in Copenhagen","date":"2024-09-27","arxiv_id":"2409.18574","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"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","sample_list":"/paper/climate-adaptation-with-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2409.18574","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.18574"}},"official":{"repos":["mlsm-at-dtu/floods_transport_rl"],"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"]}}},{"url":"/paper/curricullm-automatic-task-curricula-design","slug":"curricullm-automatic-task-curricula-design","title":"CurricuLLM: Automatic Task Curricula Design for Learning Complex Robot Skills using Large Language Models","date":"2024-09-27","arxiv_id":"2409.18382","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/curricullm-automatic-task-curricula-design#ran","syntology_url":"https://syntology.ai/paper/2409.18382","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.18382"}},"official":{"repos":["labicon/curricullm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dmc-vb-a-benchmark-for-representation","slug":"dmc-vb-a-benchmark-for-representation","title":"DMC-VB: A Benchmark for Representation Learning for Control with Visual Distractors","date":"2024-09-26","arxiv_id":"2409.18330","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_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) · 0 unverified","sample_list":"/paper/dmc-vb-a-benchmark-for-representation#ran","syntology_url":"https://syntology.ai/paper/2409.18330","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.18330"}},"official":{"repos":["google-deepmind/dmc_vision_benchmark"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/spiders-based-on-anxiety-how-reinforcement","slug":"spiders-based-on-anxiety-how-reinforcement","title":"Spiders Based on Anxiety: How Reinforcement Learning Can Deliver Desired User Experience in Virtual Reality Personalized Arachnophobia Treatment","date":"2024-09-25","arxiv_id":"2409.17406","repositories_listed":1,"syntology":null},{"url":"/paper/stage-wise-reward-shaping-for-acrobatic","slug":"stage-wise-reward-shaping-for-acrobatic","title":"Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective Reinforcement Learning Approach","date":"2024-09-24","arxiv_id":"2409.15755","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-symmetry-to-accelerate-learning-of","slug":"leveraging-symmetry-to-accelerate-learning-of","title":"Leveraging Symmetry to Accelerate Learning of Trajectory Tracking Controllers for Free-Flying Robotic Systems","date":"2024-09-17","arxiv_id":"2409.11238","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-rl-safety-with-counterfactual-llm","slug":"enhancing-rl-safety-with-counterfactual-llm","title":"Enhancing RL Safety with Counterfactual LLM Reasoning","date":"2024-09-16","arxiv_id":"2409.10188","repositories_listed":1,"syntology":null},{"url":"/paper/offline-reinforcement-learning-for-learning","slug":"offline-reinforcement-learning-for-learning","title":"Offline Reinforcement Learning for Learning to Dispatch for Job Shop Scheduling","date":"2024-09-16","arxiv_id":"2409.10589","repositories_listed":1,"syntology":null},{"url":"/paper/robust-reinforcement-learning-with-dynamic","slug":"robust-reinforcement-learning-with-dynamic","title":"Robust Reinforcement Learning with Dynamic Distortion Risk Measures","date":"2024-09-16","arxiv_id":"2409.10096","repositories_listed":1,"syntology":null},{"url":"/paper/anybipe-an-end-to-end-framework-for-training","slug":"anybipe-an-end-to-end-framework-for-training","title":"AnyBipe: An End-to-End Framework for Training and Deploying Bipedal Robots Guided by Large Language Models","date":"2024-09-13","arxiv_id":"2409.08904","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-discovers-efficient","slug":"reinforcement-learning-discovers-efficient","title":"Reinforcement Learning Discovers Efficient Decentralized Graph Path Search Strategies","date":"2024-09-12","arxiv_id":"2409.07932","repositories_listed":1,"syntology":null},{"url":"/paper/the-role-of-deep-learning-regularizations-on","slug":"the-role-of-deep-learning-regularizations-on","title":"The Role of Deep Learning Regularizations on Actors in Offline RL","date":"2024-09-11","arxiv_id":"2409.07606","repositories_listed":1,"syntology":null},{"url":"/paper/double-successive-over-relaxation-q-learning","slug":"double-successive-over-relaxation-q-learning","title":"Double Successive Over-Relaxation Q-Learning with an Extension to Deep Reinforcement Learning","date":"2024-09-10","arxiv_id":"2409.06356","repositories_listed":1,"syntology":null},{"url":"/paper/semifactual-explanations-for-reinforcement","slug":"semifactual-explanations-for-reinforcement","title":"Semifactual Explanations for Reinforcement Learning","date":"2024-09-09","arxiv_id":"2409.05435","repositories_listed":1,"syntology":null},{"url":"/paper/improving-deep-reinforcement-learning-by","slug":"improving-deep-reinforcement-learning-by","title":"Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn","date":"2024-09-07","arxiv_id":"2409.04792","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":3,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/improving-deep-reinforcement-learning-by#ran","syntology_url":"https://syntology.ai/paper/2409.04792","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.04792"}},"official":{"repos":["bluecontra/CHAIN"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/elo-rated-sequence-rewards-advancing","slug":"elo-rated-sequence-rewards-advancing","title":"ELO-Rated Sequence Rewards: Advancing Reinforcement Learning Models","date":"2024-09-05","arxiv_id":"2409.03301","repositories_listed":1,"syntology":null},{"url":"/paper/continual-diffuser-cod-mastering-continual","slug":"continual-diffuser-cod-mastering-continual","title":"Continual Diffuser (CoD): Mastering Continual Offline Reinforcement Learning with Experience Rehearsal","date":"2024-09-04","arxiv_id":"2409.02512","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-sample-efficiency-and-exploration","slug":"enhancing-sample-efficiency-and-exploration","title":"Enhancing Sample Efficiency and Exploration in Reinforcement Learning through the Integration of Diffusion Models and Proximal Policy Optimization","date":"2024-09-02","arxiv_id":"2409.01427","repositories_listed":1,"syntology":null},{"url":"/paper/mooss-mask-enhanced-temporal-contrastive","slug":"mooss-mask-enhanced-temporal-contrastive","title":"MOOSS: Mask-Enhanced Temporal Contrastive Learning for Smooth State Evolution in Visual Reinforcement Learning","date":"2024-09-02","arxiv_id":"2409.02714","repositories_listed":1,"syntology":null},{"url":"/paper/aggym-an-agricultural-biotic-stress","slug":"aggym-an-agricultural-biotic-stress","title":"AgGym: An agricultural biotic stress simulation environment for ultra-precision management planning","date":"2024-09-01","arxiv_id":"2409.00735","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-policy-policy-optimization","slug":"diffusion-policy-policy-optimization","title":"Diffusion Policy Policy Optimization","date":"2024-09-01","arxiv_id":"2409.00588","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"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","sample_list":"/paper/diffusion-policy-policy-optimization#ran","syntology_url":"https://syntology.ai/paper/2409.00588","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.00588"}},"official":null}},{"url":"/paper/traffic-expertise-meets-residual-rl-knowledge","slug":"traffic-expertise-meets-residual-rl-knowledge","title":"Traffic expertise meets residual RL: Knowledge-informed model-based residual reinforcement learning for CAV trajectory control","date":"2024-08-30","arxiv_id":"2408.17380","repositories_listed":1,"syntology":null},{"url":"/paper/rain-reinforcement-algorithms-for-improving","slug":"rain-reinforcement-algorithms-for-improving","title":"RAIN: Reinforcement Algorithms for Improving Numerical Weather and Climate Models","date":"2024-08-28","arxiv_id":"2408.16118","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"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) · 1 unverified","sample_list":"/paper/rain-reinforcement-algorithms-for-improving#ran","syntology_url":"https://syntology.ai/paper/2408.16118","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.16118"}},"official":{"repos":["p3jitnath/climate-rl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-robust-reward-machines-from-noisy","slug":"learning-robust-reward-machines-from-noisy","title":"Learning Robust Reward Machines from Noisy Labels","date":"2024-08-27","arxiv_id":"2408.14871","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_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) · 1 unverified","sample_list":"/paper/learning-robust-reward-machines-from-noisy#ran","syntology_url":"https://syntology.ai/paper/2408.14871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.14871"}},"official":{"repos":["rparac/prob-irm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/miwaves-reinforcement-learning-algorithm","slug":"miwaves-reinforcement-learning-algorithm","title":"MiWaves Reinforcement Learning Algorithm","date":"2024-08-27","arxiv_id":"2408.15076","repositories_listed":1,"syntology":null},{"url":"/paper/what-makes-math-problems-hard-for","slug":"what-makes-math-problems-hard-for","title":"What makes math problems hard for reinforcement learning: a case study","date":"2024-08-27","arxiv_id":"2408.15332","repositories_listed":1,"syntology":null},{"url":"/paper/control-informed-reinforcement-learning-for","slug":"control-informed-reinforcement-learning-for","title":"Control-Informed Reinforcement Learning for Chemical Processes","date":"2024-08-24","arxiv_id":"2408.13566","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-unlabeled-data-sharing-through","slug":"leveraging-unlabeled-data-sharing-through","title":"Leveraging Unlabeled Data Sharing through Kernel Function Approximation in Offline Reinforcement Learning","date":"2024-08-22","arxiv_id":"2408.12307","repositories_listed":1,"syntology":null},{"url":"/paper/accelerating-goal-conditioned-rl-algorithms","slug":"accelerating-goal-conditioned-rl-algorithms","title":"Accelerating Goal-Conditioned RL Algorithms and Research","date":"2024-08-20","arxiv_id":"2408.11052","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_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) · 3 unverified","sample_list":"/paper/accelerating-goal-conditioned-rl-algorithms#ran","syntology_url":"https://syntology.ai/paper/2408.11052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.11052"}},"official":{"repos":["michalbortkiewicz/jaxgcrl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/hokoff-real-game-dataset-from-honor-of-kings-1","slug":"hokoff-real-game-dataset-from-honor-of-kings-1","title":"Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks","date":"2024-08-20","arxiv_id":"2408.10556","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_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) · 0 unverified","sample_list":"/paper/hokoff-real-game-dataset-from-honor-of-kings-1#ran","syntology_url":"https://syntology.ai/paper/2408.10556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.10556"}},"official":{"repos":["tencent-ailab/hokoff"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vanilla-gradient-descent-for-oblique-decision","slug":"vanilla-gradient-descent-for-oblique-decision","title":"Vanilla Gradient Descent for Oblique Decision Trees","date":"2024-08-17","arxiv_id":"2408.09135","repositories_listed":1,"syntology":null},{"url":"/paper/fine-tuning-llms-for-autonomous-spacecraft","slug":"fine-tuning-llms-for-autonomous-spacecraft","title":"Fine-tuning LLMs for Autonomous Spacecraft Control: A Case Study Using Kerbal Space Program","date":"2024-08-16","arxiv_id":"2408.08676","repositories_listed":1,"syntology":null},{"url":"/paper/neural-reward-machines","slug":"neural-reward-machines","title":"Neural Reward Machines","date":"2024-08-16","arxiv_id":"2408.08677","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/neural-reward-machines#ran","syntology_url":"https://syntology.ai/paper/2408.08677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.08677"}},"official":{"repos":["krlgroup/neuralrewardmachines"],"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"]}}},{"url":"/paper/sympol-symbolic-tree-based-on-policy","slug":"sympol-symbolic-tree-based-on-policy","title":"Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization","date":"2024-08-16","arxiv_id":"2408.08761","repositories_listed":1,"syntology":null},{"url":"/paper/experimental-evaluation-of-offline","slug":"experimental-evaluation-of-offline","title":"Experimental evaluation of offline reinforcement learning for HVAC control in buildings","date":"2024-08-15","arxiv_id":"2408.07986","repositories_listed":1,"syntology":null},{"url":"/paper/an-introduction-to-reinforcement-learning","slug":"an-introduction-to-reinforcement-learning","title":"Introduction to Reinforcement Learning","date":"2024-08-13","arxiv_id":"2408.07712","repositories_listed":1,"syntology":null},{"url":"/paper/integrating-saliency-ranking-and","slug":"integrating-saliency-ranking-and","title":"Integrating Saliency Ranking and Reinforcement Learning for Enhanced Object Detection","date":"2024-08-13","arxiv_id":"2408.06803","repositories_listed":1,"syntology":null},{"url":"/paper/gflownet-training-by-policy-gradients","slug":"gflownet-training-by-policy-gradients","title":"GFlowNet Training by Policy Gradients","date":"2024-08-12","arxiv_id":"2408.05885","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"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) · 1 unverified","sample_list":"/paper/gflownet-training-by-policy-gradients#ran","syntology_url":"https://syntology.ai/paper/2408.05885","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.05885"}},"official":{"repos":["niupuhua1234/gfn-pg"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/listwise-reward-estimation-for-offline","slug":"listwise-reward-estimation-for-offline","title":"Listwise Reward Estimation for Offline Preference-based Reinforcement Learning","date":"2024-08-08","arxiv_id":"2408.04190","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":1,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/listwise-reward-estimation-for-offline#ran","syntology_url":"https://syntology.ai/paper/2408.04190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04190"}},"official":{"repos":["chwoong/lire"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/model-based-transfer-learning-for-contextual","slug":"model-based-transfer-learning-for-contextual","title":"Model-Based Transfer Learning for Contextual Reinforcement Learning","date":"2024-08-08","arxiv_id":"2408.04498","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/model-based-transfer-learning-for-contextual#ran","syntology_url":"https://syntology.ai/paper/2408.04498","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04498"}},"official":{"repos":["jhoon-cho/mbtl"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-rate-free-reinforcement-learning-a","slug":"learning-rate-free-reinforcement-learning-a","title":"Learning Rate-Free Reinforcement Learning: A Case for Model Selection with Non-Stationary Objectives","date":"2024-08-07","arxiv_id":"2408.04046","repositories_listed":1,"syntology":null},{"url":"/paper/2408-03195","slug":"2408-03195","title":"RELIEF: Reinforcement Learning Empowered Graph Feature Prompt Tuning","date":"2024-08-06","arxiv_id":"2408.03195","repositories_listed":1,"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":15,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/2408-03195#ran","syntology_url":"https://syntology.ai/paper/2408.03195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03195"}},"official":{"repos":["JasonZhujp/RELIEF"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-01942","slug":"2408-01942","title":"Visual Grounding for Object-Level Generalization in Reinforcement Learning","date":"2024-08-04","arxiv_id":"2408.01942","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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) · 3 unverified","sample_list":"/paper/2408-01942#ran","syntology_url":"https://syntology.ai/paper/2408.01942","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.01942"}},"official":{"repos":["pku-rl/copl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-01639","slug":"2408-01639","title":"Coordinating Planning and Tracking in Layered Control Policies via Actor-Critic Learning","date":"2024-08-03","arxiv_id":"2408.01639","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-perturbed-states-for-transformed-input","slug":"on-the-perturbed-states-for-transformed-input","title":"On the Perturbed States for Transformed Input-robust Reinforcement Learning","date":"2024-07-31","arxiv_id":"2408.00023","repositories_listed":1,"syntology":null},{"url":"/paper/collision-probability-distribution-estimation","slug":"collision-probability-distribution-estimation","title":"Collision Probability Distribution Estimation via Temporal Difference Learning","date":"2024-07-29","arxiv_id":"2407.20000","repositories_listed":1,"syntology":null},{"url":"/paper/navix-scaling-minigrid-environments-with-jax","slug":"navix-scaling-minigrid-environments-with-jax","title":"NAVIX: Scaling MiniGrid Environments with JAX","date":"2024-07-28","arxiv_id":"2407.19396","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/navix-scaling-minigrid-environments-with-jax#ran","syntology_url":"https://syntology.ai/paper/2407.19396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.19396"}},"official":{"repos":["epignatelli/navix"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/gymnasium-a-standard-interface-for","slug":"gymnasium-a-standard-interface-for","title":"Gymnasium: A Standard Interface for Reinforcement Learning Environments","date":"2024-07-24","arxiv_id":"2407.17032","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_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) · 1 unverified","sample_list":"/paper/gymnasium-a-standard-interface-for#ran","syntology_url":"https://syntology.ai/paper/2407.17032","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.17032"}},"official":{"repos":["farama-foundation/gymnasium"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-simulation-benchmark-for-autonomous-racing","slug":"a-simulation-benchmark-for-autonomous-racing","title":"A Simulation Benchmark for Autonomous Racing with Large-Scale Human Data","date":"2024-07-23","arxiv_id":"2407.16680","repositories_listed":1,"syntology":null},{"url":"/paper/functional-acceleration-for-policy-mirror","slug":"functional-acceleration-for-policy-mirror","title":"Functional Acceleration for Policy Mirror Descent","date":"2024-07-23","arxiv_id":"2407.16602","repositories_listed":1,"syntology":null},{"url":"/paper/momaland-a-set-of-benchmarks-for-multi","slug":"momaland-a-set-of-benchmarks-for-multi","title":"MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning","date":"2024-07-23","arxiv_id":"2407.16312","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-pair-trading-a-dynamic","slug":"reinforcement-learning-pair-trading-a-dynamic","title":"Reinforcement Learning Pair Trading: A Dynamic Scaling approach","date":"2024-07-23","arxiv_id":"2407.16103","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-meets-visual-odometry","slug":"reinforcement-learning-meets-visual-odometry","title":"Reinforcement Learning Meets Visual Odometry","date":"2024-07-22","arxiv_id":"2407.15626","repositories_listed":1,"syntology":null},{"url":"/paper/hard-prompts-made-interpretable-sparse","slug":"hard-prompts-made-interpretable-sparse","title":"Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL","date":"2024-07-20","arxiv_id":"2407.14733","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/hard-prompts-made-interpretable-sparse#ran","syntology_url":"https://syntology.ai/paper/2407.14733","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.14733"}},"official":{"repos":["youseob/pin"],"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"]}}},{"url":"/paper/oasis-conditional-distribution-shaping-for","slug":"oasis-conditional-distribution-shaping-for","title":"OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning","date":"2024-07-19","arxiv_id":"2407.14653","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_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) · 3 unverified","sample_list":"/paper/oasis-conditional-distribution-shaping-for#ran","syntology_url":"https://syntology.ai/paper/2407.14653","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.14653"}},"official":{"repos":["yihangyao/OASIS"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/instance-selection-for-dynamic-algorithm","slug":"instance-selection-for-dynamic-algorithm","title":"Instance Selection for Dynamic Algorithm Configuration with Reinforcement Learning: Improving Generalization","date":"2024-07-18","arxiv_id":"2407.13513","repositories_listed":1,"syntology":null},{"url":"/paper/learning-goal-conditioned-representations-for","slug":"learning-goal-conditioned-representations-for","title":"Learning Goal-Conditioned Representations for Language Reward Models","date":"2024-07-18","arxiv_id":"2407.13887","repositories_listed":1,"syntology":null},{"url":"/paper/roler-effective-reward-shaping-in-offline","slug":"roler-effective-reward-shaping-in-offline","title":"ROLeR: Effective Reward Shaping in Offline Reinforcement Learning for Recommender Systems","date":"2024-07-18","arxiv_id":"2407.13163","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-reinforcement-learning-based","slug":"understanding-reinforcement-learning-based","title":"Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Review","date":"2024-07-18","arxiv_id":"2407.13734","repositories_listed":1,"syntology":null},{"url":"/paper/chip-placement-with-diffusion","slug":"chip-placement-with-diffusion","title":"Chip Placement with Diffusion Models","date":"2024-07-17","arxiv_id":"2407.12282","repositories_listed":1,"syntology":null},{"url":"/paper/energy-guided-diffusion-sampling-for-offline","slug":"energy-guided-diffusion-sampling-for-offline","title":"Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning","date":"2024-07-17","arxiv_id":"2407.12448","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":2,"n_no_contract":4,"n_pointer_only":11,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 2 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/energy-guided-diffusion-sampling-for-offline#ran","syntology_url":"https://syntology.ai/paper/2407.12448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12448"}},"official":{"repos":["liuxhym/edis"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/variable-agnostic-causal-exploration-for","slug":"variable-agnostic-causal-exploration-for","title":"Variable-Agnostic Causal Exploration for Reinforcement Learning","date":"2024-07-17","arxiv_id":"2407.12437","repositories_listed":1,"syntology":null},{"url":"/paper/balancing-the-scales-reinforcement-learning","slug":"balancing-the-scales-reinforcement-learning","title":"Balancing the Scales: Reinforcement Learning for Fair Classification","date":"2024-07-15","arxiv_id":"2407.10629","repositories_listed":1,"syntology":null},{"url":"/paper/guidelight-industrial-solution-guidance-for","slug":"guidelight-industrial-solution-guidance-for","title":"GuideLight: \"Industrial Solution\" Guidance for More Practical Traffic Signal Control Agents","date":"2024-07-15","arxiv_id":"2407.10811","repositories_listed":1,"syntology":null},{"url":"/paper/2407-21025","slug":"2407-21025","title":"Reinforcement Learning in High-frequency Market Making","date":"2024-07-14","arxiv_id":"2407.21025","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-steer-markovian-agents-under","slug":"learning-to-steer-markovian-agents-under","title":"Learning to Steer Markovian Agents under Model Uncertainty","date":"2024-07-14","arxiv_id":"2407.10207","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_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","sample_list":"/paper/learning-to-steer-markovian-agents-under#ran","syntology_url":"https://syntology.ai/paper/2407.10207","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.10207"}},"official":{"repos":["jiaweihhuang/Steering_Markovian_Agents"],"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"]}}},{"url":"/paper/a-benchmark-environment-for-offline","slug":"a-benchmark-environment-for-offline","title":"A Benchmark Environment for Offline Reinforcement Learning in Racing Games","date":"2024-07-12","arxiv_id":"2407.09415","repositories_listed":1,"syntology":null},{"url":"/paper/transductive-active-learning-with-application","slug":"transductive-active-learning-with-application","title":"Transductive Active Learning with Application to Safe Bayesian Optimization","date":"2024-07-12","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/structural-design-through-reinforcement","slug":"structural-design-through-reinforcement","title":"Structural Design Through Reinforcement Learning","date":"2024-07-10","arxiv_id":"2407.07288","repositories_listed":1,"syntology":null},{"url":"/paper/can-learned-optimization-make-reinforcement","slug":"can-learned-optimization-make-reinforcement","title":"Can Learned Optimization Make Reinforcement Learning Less Difficult?","date":"2024-07-09","arxiv_id":"2407.07082","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_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) · 0 unverified","sample_list":"/paper/can-learned-optimization-make-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2407.07082","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07082"}},"official":{"repos":["alexgoldie/rl-learned-optimization"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/preference-guided-reinforcement-learning-for","slug":"preference-guided-reinforcement-learning-for","title":"Preference-Guided Reinforcement Learning for Efficient Exploration","date":"2024-07-09","arxiv_id":"2407.06503","repositories_listed":1,"syntology":null},{"url":"/paper/stranger-danger-identifying-and-avoiding","slug":"stranger-danger-identifying-and-avoiding","title":"Stranger Danger! Identifying and Avoiding Unpredictable Pedestrians in RL-based Social Robot Navigation","date":"2024-07-08","arxiv_id":"2407.06056","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-safety-for-autonomous-agents-in","slug":"enhancing-safety-for-autonomous-agents-in","title":"Enhancing Safety for Autonomous Agents in Partly Concealed Urban Traffic Environments Through Representation-Based Shielding","date":"2024-07-05","arxiv_id":"2407.04343","repositories_listed":1,"syntology":null},{"url":"/paper/hindsight-preference-learning-for-offline","slug":"hindsight-preference-learning-for-offline","title":"Hindsight Preference Learning for Offline Preference-based Reinforcement Learning","date":"2024-07-05","arxiv_id":"2407.04451","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/simplifying-deep-temporal-difference-learning#ran","syntology_url":"https://syntology.ai/paper/2407.04811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04811"}},"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"]}}},{"url":"/paper/craftium-an-extensible-framework-for-creating","slug":"craftium-an-extensible-framework-for-creating","title":"Craftium: An Extensible Framework for Creating Reinforcement Learning Environments","date":"2024-07-04","arxiv_id":"2407.03969","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"8 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/craftium-an-extensible-framework-for-creating#ran","syntology_url":"https://syntology.ai/paper/2407.03969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03969"}},"official":{"repos":["mikelma/craftium"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-sample-efficiency-of-reinforcement","slug":"improving-sample-efficiency-of-reinforcement","title":"Improving Sample Efficiency of Reinforcement Learning with Background Knowledge from Large Language Models","date":"2024-07-04","arxiv_id":"2407.03964","repositories_listed":1,"syntology":null},{"url":"/paper/roer-regularized-optimal-experience-replay","slug":"roer-regularized-optimal-experience-replay","title":"ROER: Regularized Optimal Experience Replay","date":"2024-07-04","arxiv_id":"2407.03995","repositories_listed":1,"syntology":null},{"url":"/paper/robocupgym-a-challenging-continuous-control","slug":"robocupgym-a-challenging-continuous-control","title":"RobocupGym: A challenging continuous control benchmark in Robocup","date":"2024-07-03","arxiv_id":"2407.14516","repositories_listed":1,"syntology":null},{"url":"/paper/physics-informed-model-and-hybrid-planning","slug":"physics-informed-model-and-hybrid-planning","title":"Physics-Informed Model and Hybrid Planning for Efficient Dyna-Style Reinforcement Learning","date":"2024-07-02","arxiv_id":"2407.02217","repositories_listed":1,"syntology":null},{"url":"/paper/dear-disentangled-environment-and-agent","slug":"dear-disentangled-environment-and-agent","title":"DEAR: Disentangled Environment and Agent Representations for Reinforcement Learning without Reconstruction","date":"2024-06-30","arxiv_id":"2407.00633","repositories_listed":1,"syntology":null},{"url":"/paper/puzzles-a-benchmark-for-neural-algorithmic","slug":"puzzles-a-benchmark-for-neural-algorithmic","title":"PUZZLES: A Benchmark for Neural Algorithmic Reasoning","date":"2024-06-29","arxiv_id":"2407.00401","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/puzzles-a-benchmark-for-neural-algorithmic#ran","syntology_url":"https://syntology.ai/paper/2407.00401","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.00401"}},"official":{"repos":["eth-disco/rlp"],"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"]}}},{"url":"/paper/contextualized-hybrid-ensemble-q-learning","slug":"contextualized-hybrid-ensemble-q-learning","title":"Contextualized Hybrid Ensemble Q-learning: Learning Fast with Control Priors","date":"2024-06-28","arxiv_id":"2406.19768","repositories_listed":1,"syntology":null},{"url":"/paper/external-model-motivated-agents-reinforcement","slug":"external-model-motivated-agents-reinforcement","title":"External Model Motivated Agents: Reinforcement Learning for Enhanced Environment Sampling","date":"2024-06-28","arxiv_id":"2407.00264","repositories_listed":1,"syntology":null},{"url":"/paper/fuzzy-logic-guided-reward-function-variation","slug":"fuzzy-logic-guided-reward-function-variation","title":"Fuzzy Logic Guided Reward Function Variation: An Oracle for Testing Reinforcement Learning Programs","date":"2024-06-28","arxiv_id":"2406.19812","repositories_listed":1,"syntology":null},{"url":"/paper/operator-world-models-for-reinforcement","slug":"operator-world-models-for-reinforcement","title":"Operator World Models for Reinforcement Learning","date":"2024-06-28","arxiv_id":"2406.19861","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-world-models-with-context-aware","slug":"efficient-world-models-with-context-aware","title":"Efficient World Models with Context-Aware Tokenization","date":"2024-06-27","arxiv_id":"2406.19320","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"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","sample_list":"/paper/efficient-world-models-with-context-aware#ran","syntology_url":"https://syntology.ai/paper/2406.19320","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19320"}},"official":{"repos":["vmicheli/delta-iris"],"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"]}}},{"url":"/paper/multi-agent-cooperative-games-using-belief","slug":"multi-agent-cooperative-games-using-belief","title":"Multi-agent Cooperative Games Using Belief Map Assisted Training","date":"2024-06-27","arxiv_id":"2406.19477","repositories_listed":1,"syntology":null},{"url":"/paper/combining-automated-optimisation-of","slug":"combining-automated-optimisation-of","title":"Combining Automated Optimisation of Hyperparameters and Reward Shape","date":"2024-06-26","arxiv_id":"2406.18293","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-foundation-world-models-for","slug":"multimodal-foundation-world-models-for","title":"GenRL: Multimodal-foundation world models for generalization in embodied agents","date":"2024-06-26","arxiv_id":"2406.18043","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multimodal-foundation-world-models-for#ran","syntology_url":"https://syntology.ai/paper/2406.18043","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18043"}},"official":{"repos":["mazpie/genrl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/ares-alternating-reinforcement-learning-and","slug":"ares-alternating-reinforcement-learning-and","title":"ARES: Alternating Reinforcement Learning and Supervised Fine-Tuning for Enhanced Multi-Modal Chain-of-Thought Reasoning Through Diverse AI Feedback","date":"2024-06-25","arxiv_id":"2407.00087","repositories_listed":1,"syntology":null},{"url":"/paper/confidence-aware-inverse-constrained","slug":"confidence-aware-inverse-constrained","title":"Confidence Aware Inverse Constrained Reinforcement Learning","date":"2024-06-24","arxiv_id":"2406.16782","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/confidence-aware-inverse-constrained#ran","syntology_url":"https://syntology.ai/paper/2406.16782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16782"}},"official":{"repos":["sriram94/confidenceawareicrl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/kehrl-learning-knowledge-enhanced-language","slug":"kehrl-learning-knowledge-enhanced-language","title":"KEHRL: Learning Knowledge-Enhanced Language Representations with Hierarchical Reinforcement Learning","date":"2024-06-24","arxiv_id":"2406.16374","repositories_listed":1,"syntology":null}],"record_sha256":"4e60f10d81d4f0fcb5cdfe0cd8eec6ebe58badf3ec62d99bf32f591ba50f027e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}