{"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/deep-reinforcement-learning/papers/6","list_of":"/task/deep-reinforcement-learning","task":"Deep Reinforcement Learning","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":6,"pages_in_order":59,"rows_per_page":100,"rows":[501,600],"of":5822,"counts":{"archive_papers_tagged":5822,"with_a_code_link":1739,"where_syntology_ran_a_sample":398,"not_listed_spam_title":0,"listed":5822,"listed_where_code_ran":398,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":340,"every_run_a_failure_of_syntologys_instrument":58,"listed_with_a_run_with_no_instrument_failure":340,"listed_every_run_a_failure_of_syntologys_instrument":58,"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/deep-reinforcement-learning","prev":"/task/deep-reinforcement-learning/papers/5","next":"/task/deep-reinforcement-learning/papers/7","papers":[{"url":"/paper/semantic-aware-spectrum-sharing-in-internet","slug":"semantic-aware-spectrum-sharing-in-internet","title":"Semantic-Aware Spectrum Sharing in Internet of Vehicles Based on Deep Reinforcement Learning","date":"2024-06-11","arxiv_id":"2406.07213","repositories_listed":1,"syntology":null},{"url":"/paper/is-value-functions-estimation-with","slug":"is-value-functions-estimation-with","title":"Is Value Functions Estimation with Classification Plug-and-play for Offline Reinforcement Learning?","date":"2024-06-10","arxiv_id":"2406.06309","repositories_listed":1,"syntology":null},{"url":"/paper/towards-real-world-efficiency-domain","slug":"towards-real-world-efficiency-domain","title":"Towards Real-World Efficiency: Domain Randomization in Reinforcement Learning for Pre-Capture of Free-Floating Moving Targets by Autonomous Robots","date":"2024-06-10","arxiv_id":"2406.06460","repositories_listed":1,"syntology":null},{"url":"/paper/probabilistic-perspectives-on-error","slug":"probabilistic-perspectives-on-error","title":"Probabilistic Perspectives on Error Minimization in Adversarial Reinforcement Learning","date":"2024-06-07","arxiv_id":"2406.04724","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"10 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/probabilistic-perspectives-on-error#ran","syntology_url":"https://syntology.ai/paper/2406.04724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04724"}},"official":{"repos":["romanbelaire/acoe-robust-rl"],"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":["found_in_text","official"]}}},{"url":"/paper/learning-to-play-air-hockey-with-model-based","slug":"learning-to-play-air-hockey-with-model-based","title":"Learning to Play Air Hockey with Model-Based Deep Reinforcement Learning","date":"2024-06-01","arxiv_id":"2406.00518","repositories_listed":1,"syntology":null},{"url":"/paper/adesse-advice-explanations-in-complex","slug":"adesse-advice-explanations-in-complex","title":"ADESSE: Advice Explanations in Complex Repeated Decision-Making Environments","date":"2024-05-31","arxiv_id":"2405.20705","repositories_listed":1,"syntology":null},{"url":"/paper/amortizing-intractable-inference-in-diffusion","slug":"amortizing-intractable-inference-in-diffusion","title":"Amortizing intractable inference in diffusion models for vision, language, and control","date":"2024-05-31","arxiv_id":"2405.20971","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":14,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/amortizing-intractable-inference-in-diffusion#ran","syntology_url":"https://syntology.ai/paper/2405.20971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20971"}},"official":{"repos":["gfnorg/diffusion-finetuning"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/opentensor-reproducing-faster-matrix","slug":"opentensor-reproducing-faster-matrix","title":"OpenTensor: Reproducing Faster Matrix Multiplication Discovering Algorithms","date":"2024-05-31","arxiv_id":"2405.20748","repositories_listed":1,"syntology":null},{"url":"/paper/aquatic-navigation-a-challenging-benchmark","slug":"aquatic-navigation-a-challenging-benchmark","title":"Aquatic Navigation: A Challenging Benchmark for Deep Reinforcement Learning","date":"2024-05-30","arxiv_id":"2405.20534","repositories_listed":1,"syntology":null},{"url":"/paper/a-study-of-plasticity-loss-in-on-policy-deep","slug":"a-study-of-plasticity-loss-in-on-policy-deep","title":"A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning","date":"2024-05-29","arxiv_id":"2405.19153","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"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) · 4 unverified","sample_list":"/paper/a-study-of-plasticity-loss-in-on-policy-deep#ran","syntology_url":"https://syntology.ai/paper/2405.19153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19153"}},"official":{"repos":["awjuliani/deep-rl-plasticity"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/statistical-context-detection-for-deep","slug":"statistical-context-detection-for-deep","title":"Statistical Context Detection for Deep Lifelong Reinforcement Learning","date":"2024-05-29","arxiv_id":"2405.19047","repositories_listed":1,"syntology":null},{"url":"/paper/verifiably-robust-conformal-prediction","slug":"verifiably-robust-conformal-prediction","title":"Verifiably Robust Conformal Prediction","date":"2024-05-29","arxiv_id":"2405.18942","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":2,"n_ran_checked":3,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":10,"phrase":"8 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/verifiably-robust-conformal-prediction#ran","syntology_url":"https://syntology.ai/paper/2405.18942","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.18942"}},"official":{"repos":["ddv-lab/Verifiably_Robust_CP"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-reinforcement-learning-with-enhanced-ppo","slug":"deep-reinforcement-learning-with-enhanced-ppo","title":"Deep Reinforcement Learning with Enhanced PPO for Safe Mobile Robot Navigation","date":"2024-05-25","arxiv_id":"2405.16266","repositories_listed":1,"syntology":null},{"url":"/paper/interpretable-and-editable-programmatic-tree","slug":"interpretable-and-editable-programmatic-tree","title":"Interpretable and Editable Programmatic Tree Policies for Reinforcement Learning","date":"2024-05-23","arxiv_id":"2405.14956","repositories_listed":1,"syntology":null},{"url":"/paper/formally-verifying-deep-reinforcement","slug":"formally-verifying-deep-reinforcement","title":"Formally Verifying Deep Reinforcement Learning Controllers with Lyapunov Barrier Certificates","date":"2024-05-22","arxiv_id":"2405.14058","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/formally-verifying-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2405.14058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14058"}},"official":{"repos":["neuralnetworkverification/artifact-fmcad24-docking"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/learning-to-play-atari-games-using-dueling-q","slug":"learning-to-play-atari-games-using-dueling-q","title":"Learning To Play Atari Games Using Dueling Q-Learning and Hebbian Plasticity","date":"2024-05-22","arxiv_id":"2405.13960","repositories_listed":1,"syntology":null},{"url":"/paper/uncertainty-aware-drl-for-autonomous-vehicle","slug":"uncertainty-aware-drl-for-autonomous-vehicle","title":"Uncertainty-Aware DRL for Autonomous Vehicle Crowd Navigation in Shared Space","date":"2024-05-22","arxiv_id":"2405.13969","repositories_listed":1,"syntology":null},{"url":"/paper/robust-deep-reinforcement-learning-with-1","slug":"robust-deep-reinforcement-learning-with-1","title":"Robust Deep Reinforcement Learning with Adaptive Adversarial Perturbations in Action Space","date":"2024-05-20","arxiv_id":"2405.11982","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_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","sample_list":"/paper/robust-deep-reinforcement-learning-with-1#ran","syntology_url":"https://syntology.ai/paper/2405.11982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.11982"}},"official":{"repos":["lqm00/a2p-sac"],"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"]}}},{"url":"/paper/rice-breaking-through-the-training","slug":"rice-breaking-through-the-training","title":"RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation","date":"2024-05-05","arxiv_id":"2405.03064","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"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 1 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/rice-breaking-through-the-training#ran","syntology_url":"https://syntology.ai/paper/2405.03064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.03064"}},"official":{"repos":["chengzelei/rice"],"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":["found_in_text","official"]}}},{"url":"/paper/hand-object-interaction-controller-hoic-deep","slug":"hand-object-interaction-controller-hoic-deep","title":"Hand-Object Interaction Controller (HOIC): Deep Reinforcement Learning for Reconstructing Interactions with Physics","date":"2024-05-04","arxiv_id":"2405.02676","repositories_listed":1,"syntology":null},{"url":"/paper/proximal-curriculum-with-task-correlations","slug":"proximal-curriculum-with-task-correlations","title":"Proximal Curriculum with Task Correlations for Deep Reinforcement Learning","date":"2024-05-03","arxiv_id":"2405.02481","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-procedural-generation-for-learning","slug":"leveraging-procedural-generation-for-learning","title":"Leveraging Procedural Generation for Learning Autonomous Peg-in-Hole Assembly in Space","date":"2024-05-02","arxiv_id":"2405.01134","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-reinforcement-learning-for-robot","slug":"adaptive-reinforcement-learning-for-robot","title":"Task and Domain Adaptive Reinforcement Learning for Robot Control","date":"2024-04-29","arxiv_id":"2404.18713","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_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","sample_list":"/paper/dpo-meets-ppo-reinforced-token-optimization#ran","syntology_url":"https://syntology.ai/paper/2404.18922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18922"}},"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"]}}},{"url":"/paper/safe-rl-saliency-aware-counterfactual","slug":"safe-rl-saliency-aware-counterfactual","title":"SAFE-RL: Saliency-Aware Counterfactual Explainer for Deep Reinforcement Learning Policies","date":"2024-04-28","arxiv_id":"2404.18326","repositories_listed":1,"syntology":null},{"url":"/paper/learning-manipulation-tasks-in-dynamic-and","slug":"learning-manipulation-tasks-in-dynamic-and","title":"Learning Manipulation Tasks in Dynamic and Shared 3D Spaces","date":"2024-04-26","arxiv_id":"2404.17673","repositories_listed":1,"syntology":null},{"url":"/paper/swarmrl-building-the-future-of-smart-active","slug":"swarmrl-building-the-future-of-smart-active","title":"SwarmRL: Building the Future of Smart Active Systems","date":"2024-04-25","arxiv_id":"2404.16388","repositories_listed":1,"syntology":null},{"url":"/paper/a-fast-balance-optimization-approach-for","slug":"a-fast-balance-optimization-approach-for","title":"A fast balance optimization approach for charging enhancement of lithium-ion battery packs through deep reinforcement learning","date":"2024-04-24","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-regularization-of-representation","slug":"adaptive-regularization-of-representation","title":"Adaptive Regularization of Representation Rank as an Implicit Constraint of Bellman Equation","date":"2024-04-19","arxiv_id":"2404.12754","repositories_listed":1,"syntology":null},{"url":"/paper/deep-reinforcement-learning-for-personalized-1","slug":"deep-reinforcement-learning-for-personalized-1","title":"Deep Reinforcement Learning for Personalized Diagnostic Decision Pathways Using Electronic Health Records: A Comparative Study on Anemia and Systemic Lupus Erythematosus","date":"2024-04-09","arxiv_id":"2404.05913","repositories_listed":1,"syntology":null},{"url":"/paper/learning-efficient-and-fair-policies-for","slug":"learning-efficient-and-fair-policies-for","title":"Learning Efficient and Fair Policies for Uncertainty-Aware Collaborative Human-Robot Order Picking","date":"2024-04-09","arxiv_id":"2404.08006","repositories_listed":1,"syntology":null},{"url":"/paper/learning-heuristics-for-transit-network","slug":"learning-heuristics-for-transit-network","title":"Learning Heuristics for Transit Network Design and Improvement with Deep Reinforcement Learning","date":"2024-04-08","arxiv_id":"2404.05894","repositories_listed":1,"syntology":null},{"url":"/paper/a-ppo-based-drl-auto-tuning-nonlinear-pid","slug":"a-ppo-based-drl-auto-tuning-nonlinear-pid","title":"AirPilot: Interpretable PPO-based DRL Auto-Tuned Nonlinear PID Drone Controller for Robust Autonomous Flights","date":"2024-03-30","arxiv_id":"2404.00204","repositories_listed":1,"syntology":null},{"url":"/paper/intent-aware-drl-based-uplink-dynamic","slug":"intent-aware-drl-based-uplink-dynamic","title":"Intent-Aware DRL-Based NOMA Uplink Dynamic Scheduler for IIoT","date":"2024-03-27","arxiv_id":"2403.18364","repositories_listed":1,"syntology":null},{"url":"/paper/footstepnet-an-efficient-actor-critic-method","slug":"footstepnet-an-efficient-actor-critic-method","title":"FootstepNet: an Efficient Actor-Critic Method for Fast On-line Bipedal Footstep Planning and Forecasting","date":"2024-03-19","arxiv_id":"2403.12589","repositories_listed":1,"syntology":null},{"url":"/paper/quality-diversity-actor-critic-learning-high","slug":"quality-diversity-actor-critic-learning-high","title":"Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics","date":"2024-03-15","arxiv_id":"2403.09930","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/quality-diversity-actor-critic-learning-high#ran","syntology_url":"https://syntology.ai/paper/2403.09930","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09930"}},"official":{"repos":["adaptive-intelligent-robotics/qdac"],"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"]}}},{"url":"/paper/incorporating-graph-attention-mechanism-into-1","slug":"incorporating-graph-attention-mechanism-into-1","title":"Incorporating Graph Attention Mechanism into Geometric Problem Solving Based on Deep Reinforcement Learning","date":"2024-03-14","arxiv_id":"2403.14690","repositories_listed":1,"syntology":null},{"url":"/paper/sindy-rl-interpretable-and-efficient-model","slug":"sindy-rl-interpretable-and-efficient-model","title":"SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning","date":"2024-03-14","arxiv_id":"2403.09110","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/sindy-rl-interpretable-and-efficient-model#ran","syntology_url":"https://syntology.ai/paper/2403.09110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09110"}},"official":{"repos":["nzolman/sindy-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"]}}},{"url":"/paper/lander-ai-adaptive-landing-behavior-agent-for","slug":"lander-ai-adaptive-landing-behavior-agent-for","title":"Lander.AI: Adaptive Landing Behavior Agent for Expertise in 3D Dynamic Platform Landings","date":"2024-03-11","arxiv_id":"2403.06572","repositories_listed":1,"syntology":null},{"url":"/paper/symmetry-considerations-for-learning-task","slug":"symmetry-considerations-for-learning-task","title":"Symmetry Considerations for Learning Task Symmetric Robot Policies","date":"2024-03-07","arxiv_id":"2403.04359","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-solve-job-shop-scheduling-under","slug":"learning-to-solve-job-shop-scheduling-under","title":"Learning to Solve Job Shop Scheduling under Uncertainty","date":"2024-03-04","arxiv_id":"2404.01308","repositories_listed":1,"syntology":null},{"url":"/paper/towards-fair-and-efficient-learning-based","slug":"towards-fair-and-efficient-learning-based","title":"Towards Fair and Efficient Learning-based Congestion Control","date":"2024-03-04","arxiv_id":"2403.01798","repositories_listed":1,"syntology":null},{"url":"/paper/a-holistic-power-optimization-approach-for","slug":"a-holistic-power-optimization-approach-for","title":"A Holistic Power Optimization Approach for Microgrid Control Based on Deep Reinforcement Learning","date":"2024-03-01","arxiv_id":"2403.01013","repositories_listed":1,"syntology":null},{"url":"/paper/snapshot-reinforcement-learning-leveraging","slug":"snapshot-reinforcement-learning-leveraging","title":"Snapshot Reinforcement Learning: Leveraging Prior Trajectories for Efficiency","date":"2024-03-01","arxiv_id":"2403.00673","repositories_listed":1,"syntology":null},{"url":"/paper/a-model-based-approach-for-improving","slug":"a-model-based-approach-for-improving","title":"A Model-Based Approach for Improving Reinforcement Learning Efficiency Leveraging Expert Observations","date":"2024-02-29","arxiv_id":"2402.18836","repositories_listed":1,"syntology":null},{"url":"/paper/symmetry-aware-reinforcement-learning-for","slug":"symmetry-aware-reinforcement-learning-for","title":"Symmetry-aware Reinforcement Learning for Robotic Assembly under Partial Observability with a Soft Wrist","date":"2024-02-28","arxiv_id":"2402.18002","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/symmetry-aware-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/2402.18002","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18002"}},"official":{"repos":["omron-sinicx/symmetry-aware-pomdp"],"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/beacon-a-lightweight-deep-reinforcement","slug":"beacon-a-lightweight-deep-reinforcement","title":"Beacon, a lightweight deep reinforcement learning benchmark library for flow control","date":"2024-02-27","arxiv_id":"2402.17402","repositories_listed":1,"syntology":null},{"url":"/paper/flexible-robust-beamforming-for-multibeam","slug":"flexible-robust-beamforming-for-multibeam","title":"Flexible Robust Beamforming for Multibeam Satellite Downlink using Reinforcement Learning","date":"2024-02-26","arxiv_id":"2402.16563","repositories_listed":1,"syntology":null},{"url":"/paper/model-based-deep-reinforcement-learning-for-2","slug":"model-based-deep-reinforcement-learning-for-2","title":"Model-based deep reinforcement learning for accelerated learning from flow simulations","date":"2024-02-26","arxiv_id":"2402.16543","repositories_listed":1,"syntology":null},{"url":"/paper/scalable-volt-var-optimization-using-rllib","slug":"scalable-volt-var-optimization-using-rllib","title":"Scalable Volt-VAR Optimization using RLlib-IMPALA Framework: A Reinforcement Learning Approach","date":"2024-02-24","arxiv_id":"2402.15932","repositories_listed":1,"syntology":null},{"url":"/paper/transformable-gaussian-reward-function-for","slug":"transformable-gaussian-reward-function-for","title":"Transformable Gaussian Reward Function for Socially-Aware Navigation with Deep Reinforcement Learning","date":"2024-02-22","arxiv_id":"2402.14569","repositories_listed":1,"syntology":null},{"url":"/paper/analyzing-operator-states-and-the-impact-of","slug":"analyzing-operator-states-and-the-impact-of","title":"Analyzing Operator States and the Impact of AI-Enhanced Decision Support in Control Rooms: A Human-in-the-Loop Specialized Reinforcement Learning Framework for Intervention Strategies","date":"2024-02-20","arxiv_id":"2402.13219","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-data-augmentation-in-deep","slug":"revisiting-data-augmentation-in-deep","title":"Revisiting Data Augmentation in Deep Reinforcement Learning","date":"2024-02-19","arxiv_id":"2402.12181","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 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; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/revisiting-data-augmentation-in-deep#ran","syntology_url":"https://syntology.ai/paper/2402.12181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12181"}},"official":{"repos":["jianshu-hu/drqv2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/risk-sensitive-soft-actor-critic-for-robust","slug":"risk-sensitive-soft-actor-critic-for-robust","title":"Risk-Sensitive Soft Actor-Critic for Robust Deep Reinforcement Learning under Distribution Shifts","date":"2024-02-15","arxiv_id":"2402.09992","repositories_listed":1,"syntology":null},{"url":"/paper/fgeo-drl-deductive-reasoning-for-geometric","slug":"fgeo-drl-deductive-reasoning-for-geometric","title":"FGeo-DRL: Deductive Reasoning for Geometric Problems through Deep Reinforcement Learning","date":"2024-02-14","arxiv_id":"2402.09051","repositories_listed":1,"syntology":null},{"url":"/paper/deep-reinforcement-learning-for-controlled","slug":"deep-reinforcement-learning-for-controlled","title":"Deep Reinforcement Learning for Controlled Traversing of the Attractor Landscape of Boolean Models in the Context of Cellular Reprogramming","date":"2024-02-13","arxiv_id":"2402.08491","repositories_listed":1,"syntology":null},{"url":"/paper/a-competition-winning-deep-reinforcement","slug":"a-competition-winning-deep-reinforcement","title":"A Competition Winning Deep Reinforcement Learning Agent in microRTS","date":"2024-02-12","arxiv_id":"2402.08112","repositories_listed":1,"syntology":null},{"url":"/paper/solving-deep-reinforcement-learning","slug":"solving-deep-reinforcement-learning","title":"Solving Deep Reinforcement Learning Tasks with Evolution Strategies and Linear Policy Networks","date":"2024-02-10","arxiv_id":"2402.06912","repositories_listed":1,"syntology":null},{"url":"/paper/decision-theory-guided-deep-reinforcement","slug":"decision-theory-guided-deep-reinforcement","title":"Decision Theory-Guided Deep Reinforcement Learning for Fast Learning","date":"2024-02-08","arxiv_id":"2402.06023","repositories_listed":1,"syntology":null},{"url":"/paper/deep-reinforcement-learning-with-dynamic-1","slug":"deep-reinforcement-learning-with-dynamic-1","title":"Deep Reinforcement Learning with Dynamic Graphs for Adaptive Informative Path Planning","date":"2024-02-07","arxiv_id":"2402.04894","repositories_listed":1,"syntology":null},{"url":"/paper/language-based-augmentation-to-address","slug":"language-based-augmentation-to-address","title":"Language-Based Augmentation to Address Shortcut Learning in Object Goal Navigation","date":"2024-02-07","arxiv_id":"2402.05090","repositories_listed":1,"syntology":null},{"url":"/paper/joint-intrinsic-motivation-for-coordinated","slug":"joint-intrinsic-motivation-for-coordinated","title":"Joint Intrinsic Motivation for Coordinated Exploration in Multi-Agent Deep Reinforcement Learning","date":"2024-02-06","arxiv_id":"2402.03972","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-with-ensemble-model","slug":"reinforcement-learning-with-ensemble-model","title":"Reinforcement Learning with Ensemble Model Predictive Safety Certification","date":"2024-02-06","arxiv_id":"2402.04182","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_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","sample_list":"/paper/reinforcement-learning-with-ensemble-model#ran","syntology_url":"https://syntology.ai/paper/2402.04182","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04182"}},"official":{"repos":["svengronauer/x-mpsc"],"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"]}}},{"url":"/paper/invit-a-generalizable-routing-problem-solver","slug":"invit-a-generalizable-routing-problem-solver","title":"INViT: A Generalizable Routing Problem Solver with Invariant Nested View Transformer","date":"2024-02-04","arxiv_id":"2402.02317","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":12,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/invit-a-generalizable-routing-problem-solver#ran","syntology_url":"https://syntology.ai/paper/2402.02317","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02317"}},"official":{"repos":["kasumigaoka-utaha/invit"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/developing-a-multi-agent-and-self-adaptive","slug":"developing-a-multi-agent-and-self-adaptive","title":"Developing A Multi-Agent and Self-Adaptive Framework with Deep Reinforcement Learning for Dynamic Portfolio Risk Management","date":"2024-02-01","arxiv_id":"2402.00515","repositories_listed":1,"syntology":null},{"url":"/paper/raddqn-a-deep-q-learning-based-architecture","slug":"raddqn-a-deep-q-learning-based-architecture","title":"RadDQN: a Deep Q Learning-based Architecture for Finding Time-efficient Minimum Radiation Exposure Pathway","date":"2024-02-01","arxiv_id":"2402.00468","repositories_listed":1,"syntology":null},{"url":"/paper/vertical-symbolic-regression-via-deep-policy","slug":"vertical-symbolic-regression-via-deep-policy","title":"Vertical Symbolic Regression via Deep Policy Gradient","date":"2024-02-01","arxiv_id":"2402.00254","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"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) · 0 unverified","sample_list":"/paper/vertical-symbolic-regression-via-deep-policy#ran","syntology_url":"https://syntology.ai/paper/2402.00254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00254"}},"official":{"repos":["jiangnanhugo/vsr-dpg"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/core-towards-scalable-and-efficient-causal","slug":"core-towards-scalable-and-efficient-causal","title":"CORE: Towards Scalable and Efficient Causal Discovery with Reinforcement Learning","date":"2024-01-30","arxiv_id":"2401.16974","repositories_listed":1,"syntology":null},{"url":"/paper/effective-communication-with-dynamic-feature","slug":"effective-communication-with-dynamic-feature","title":"Effective Communication with Dynamic Feature Compression","date":"2024-01-29","arxiv_id":"2401.16236","repositories_listed":1,"syntology":null},{"url":"/paper/the-definitive-guide-to-policy-gradients-in","slug":"the-definitive-guide-to-policy-gradients-in","title":"The Definitive Guide to Policy Gradients in Deep Reinforcement Learning: Theory, Algorithms and Implementations","date":"2024-01-24","arxiv_id":"2401.13662","repositories_listed":1,"syntology":null},{"url":"/paper/asynchronous-parallel-reinforcement-learning","slug":"asynchronous-parallel-reinforcement-learning","title":"Asynchronous Parallel Reinforcement Learning for Optimizing Propulsive Performance in Fin Ray Control","date":"2024-01-21","arxiv_id":"2401.11349","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-system-level-safety-in-mixed","slug":"enhancing-system-level-safety-in-mixed","title":"Enhancing System-Level Safety in Mixed-Autonomy Platoon via Safe Reinforcement Learning","date":"2024-01-20","arxiv_id":"2401.11148","repositories_listed":1,"syntology":null},{"url":"/paper/cooperative-edge-caching-based-on-elastic","slug":"cooperative-edge-caching-based-on-elastic","title":"Cooperative Edge Caching Based on Elastic Federated and Multi-Agent Deep Reinforcement Learning in Next-Generation Network","date":"2024-01-18","arxiv_id":"2401.09886","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-state-and-history-representations","slug":"bridging-state-and-history-representations","title":"Bridging State and History Representations: Understanding Self-Predictive RL","date":"2024-01-17","arxiv_id":"2401.08898","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":9,"phrase":"8 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bridging-state-and-history-representations#ran","syntology_url":"https://syntology.ai/paper/2401.08898","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.08898"}},"official":{"repos":["twni2016/self-predictive-rl"],"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":["official"]}}},{"url":"/paper/sharing-knowledge-in-multi-task-deep-1","slug":"sharing-knowledge-in-multi-task-deep-1","title":"Sharing Knowledge in Multi-Task Deep Reinforcement Learning","date":"2024-01-17","arxiv_id":"2401.09561","repositories_listed":1,"syntology":null},{"url":"/paper/a-semantic-aware-multiple-access-scheme-for","slug":"a-semantic-aware-multiple-access-scheme-for","title":"A Semantic-Aware Multiple Access Scheme for Distributed, Dynamic 6G-Based Applications","date":"2024-01-12","arxiv_id":"2401.06308","repositories_listed":1,"syntology":null},{"url":"/paper/personalized-reinforcement-learning-with-a","slug":"personalized-reinforcement-learning-with-a","title":"Personalized Reinforcement Learning with a Budget of Policies","date":"2024-01-12","arxiv_id":"2401.06514","repositories_listed":1,"syntology":null},{"url":"/paper/an-experimental-evaluation-of-deep","slug":"an-experimental-evaluation-of-deep","title":"An experimental evaluation of Deep Reinforcement Learning algorithms for HVAC control","date":"2024-01-11","arxiv_id":"2401.05737","repositories_listed":1,"syntology":null},{"url":"/paper/interpretable-concept-bottlenecks-to-align","slug":"interpretable-concept-bottlenecks-to-align","title":"Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents","date":"2024-01-11","arxiv_id":"2401.05821","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_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) · 0 unverified","sample_list":"/paper/interpretable-concept-bottlenecks-to-align#ran","syntology_url":"https://syntology.ai/paper/2401.05821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.05821"}},"official":{"repos":["k4ntz/scobots"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-objective-prioritized-workflow","slug":"multi-objective-prioritized-workflow","title":"Multi Objective Prioritized Workflow Scheduling Using Deep Reinforcement Based Learning in Cloud Computing","date":"2024-01-08","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/human-as-ai-mentor-enhanced-human-in-the-loop","slug":"human-as-ai-mentor-enhanced-human-in-the-loop","title":"HAIM-DRL: Enhanced Human-in-the-loop Reinforcement Learning for Safe and Efficient Autonomous Driving","date":"2024-01-06","arxiv_id":"2401.03160","repositories_listed":1,"syntology":null},{"url":"/paper/spqr-controlling-q-ensemble-independence-with-1","slug":"spqr-controlling-q-ensemble-independence-with-1","title":"SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning","date":"2024-01-06","arxiv_id":"2401.03137","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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) · 3 unverified","sample_list":"/paper/spqr-controlling-q-ensemble-independence-with-1#ran","syntology_url":"https://syntology.ai/paper/2401.03137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03137"}},"official":{"repos":["dohyeoklee/SPQR"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/data-assimilation-in-chaotic-systems-using","slug":"data-assimilation-in-chaotic-systems-using","title":"Data Assimilation in Chaotic Systems Using Deep Reinforcement Learning","date":"2024-01-01","arxiv_id":"2401.00916","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-trajectory-constrained-exploration","slug":"adaptive-trajectory-constrained-exploration","title":"Adaptive trajectory-constrained exploration strategy for deep reinforcement learning","date":"2023-12-27","arxiv_id":"2312.16456","repositories_listed":1,"syntology":null},{"url":"/paper/xuance-a-comprehensive-and-unified-deep","slug":"xuance-a-comprehensive-and-unified-deep","title":"XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library","date":"2023-12-25","arxiv_id":"2312.16248","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/xuance-a-comprehensive-and-unified-deep#ran","syntology_url":"https://syntology.ai/paper/2312.16248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.16248"}},"official":{"repos":["agi-brain/xuance"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/madi-learning-to-mask-distractions-for","slug":"madi-learning-to-mask-distractions-for","title":"MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning","date":"2023-12-23","arxiv_id":"2312.15339","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/madi-learning-to-mask-distractions-for#ran","syntology_url":"https://syntology.ai/paper/2312.15339","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15339"}},"official":{"repos":["bramgrooten/mask-distractions"],"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/not-all-tasks-are-equally-difficult-multi","slug":"not-all-tasks-are-equally-difficult-multi","title":"Not All Tasks Are Equally Difficult: Multi-Task Deep Reinforcement Learning with Dynamic Depth Routing","date":"2023-12-22","arxiv_id":"2312.14472","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_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) · 4 unverified","sample_list":"/paper/not-all-tasks-are-equally-difficult-multi#ran","syntology_url":"https://syntology.ai/paper/2312.14472","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14472"}},"official":{"repos":["DarkDawn233/D2R_MTRL"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/parameterized-decision-making-with-multi","slug":"parameterized-decision-making-with-multi","title":"Parameterized Decision-making with Multi-modal Perception for Autonomous Driving","date":"2023-12-19","arxiv_id":"2312.11935","repositories_listed":1,"syntology":null},{"url":"/paper/animal-ai-3-what-s-new-why-you-should-care","slug":"animal-ai-3-what-s-new-why-you-should-care","title":"The Animal-AI Environment: A Virtual Laboratory For Comparative Cognition and Artificial Intelligence Research","date":"2023-12-18","arxiv_id":"2312.11414","repositories_listed":1,"syntology":null},{"url":"/paper/colored-noise-in-ppo-improved-exploration-and","slug":"colored-noise-in-ppo-improved-exploration-and","title":"Colored Noise in PPO: Improved Exploration and Performance through Correlated Action Sampling","date":"2023-12-18","arxiv_id":"2312.11091","repositories_listed":1,"syntology":null},{"url":"/paper/generalization-analysis-of-policy-networks-an","slug":"generalization-analysis-of-policy-networks-an","title":"Analyzing Generalization in Policy Networks: A Case Study with the Double-Integrator System","date":"2023-12-16","arxiv_id":"2312.10472","repositories_listed":1,"syntology":null},{"url":"/paper/improving-environment-robustness-of-deep","slug":"improving-environment-robustness-of-deep","title":"Improving Environment Robustness of Deep Reinforcement Learning Approaches for Autonomous Racing Using Bayesian Optimization-based Curriculum Learning","date":"2023-12-16","arxiv_id":"2312.10557","repositories_listed":1,"syntology":null},{"url":"/paper/global-rewards-in-multi-agent-deep","slug":"global-rewards-in-multi-agent-deep","title":"Global Rewards in Multi-Agent Deep Reinforcement Learning for Autonomous Mobility on Demand Systems","date":"2023-12-14","arxiv_id":"2312.08884","repositories_listed":1,"syntology":null},{"url":"/paper/multi-agent-deep-reinforcement-learning-based-3","slug":"multi-agent-deep-reinforcement-learning-based-3","title":"Multi-agent deep reinforcement learning based real-time planning approach for responsive customized bus routes","date":"2023-12-14","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/i-open-at-the-close-a-deep-reinforcement","slug":"i-open-at-the-close-a-deep-reinforcement","title":"I Open at the Close: A Deep Reinforcement Learning Evaluation of Open Streets Initiatives","date":"2023-12-12","arxiv_id":"2312.07680","repositories_listed":1,"syntology":null},{"url":"/paper/no-prior-mask-eliminate-redundant-action-for","slug":"no-prior-mask-eliminate-redundant-action-for","title":"No Prior Mask: Eliminate Redundant Action for Deep Reinforcement Learning","date":"2023-12-11","arxiv_id":"2312.06258","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":6,"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/no-prior-mask-eliminate-redundant-action-for#ran","syntology_url":"https://syntology.ai/paper/2312.06258","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06258"}},"official":{"repos":["zhongdy15/npm"],"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/distributional-bellman-operators-over-mean","slug":"distributional-bellman-operators-over-mean","title":"Distributional Bellman Operators over Mean Embeddings","date":"2023-12-09","arxiv_id":"2312.07358","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-the-gaps-learning-verifiable-model","slug":"bridging-the-gaps-learning-verifiable-model","title":"MPC-Inspired Reinforcement Learning for Verifiable Model-Free Control","date":"2023-12-08","arxiv_id":"2312.05332","repositories_listed":1,"syntology":null},{"url":"/paper/adsorbrl-deep-multi-objective-reinforcement","slug":"adsorbrl-deep-multi-objective-reinforcement","title":"AdsorbRL: Deep Multi-Objective Reinforcement Learning for Inverse Catalysts Design","date":"2023-12-04","arxiv_id":"2312.02308","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adsorbrl-deep-multi-objective-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2312.02308","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02308"}},"official":{"repos":["rlacombe/adsorbrl"],"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/class-symbolic-regression-gotta-fit-em-all","slug":"class-symbolic-regression-gotta-fit-em-all","title":"Class Symbolic Regression: Gotta Fit 'Em All","date":"2023-12-04","arxiv_id":"2312.01816","repositories_listed":1,"syntology":null}],"record_sha256":"207d128ba1a6d1492a5bb98cc6645b55206520b6ae3186026d498a328c57da01","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}