{"url":"/task/rllib","name":"rllib","slug":"rllib","description_markdown":null,"categories":[{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":23,"papers_with_code":16,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":16,"of":16,"tagged_in_all":23,"items":[{"url":"/paper/popgym-benchmarking-partially-observable","title":"POPGym: Benchmarking Partially Observable Reinforcement Learning","date":"2023-03-03","arxiv_id":"2303.01859","repositories_listed":3,"syntology":null},{"url":"/paper/rllib-abstractions-for-distributed","title":"RLlib: Abstractions for Distributed Reinforcement Learning","date":"2017-12-26","arxiv_id":"1712.09381","repositories_listed":3,"syntology":null},{"url":"/paper/ixdrl-a-novel-explainable-deep-reinforcement","title":"IxDRL: A Novel Explainable Deep Reinforcement Learning Toolkit based on Analyses of Interestingness","date":"2023-07-18","arxiv_id":"2307.08933","repositories_listed":2,"syntology":null},{"url":"/paper/socialjax-an-evaluation-suite-for-multi-agent","title":"SocialJax: An Evaluation Suite for Multi-agent Reinforcement Learning in Sequential Social Dilemmas","date":"2025-03-18","arxiv_id":"2503.14576","repositories_listed":1,"syntology":{"n":11,"n_ran":0,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/highly-parallelized-reinforcement-learning","title":"Highly Parallelized Reinforcement Learning Training with Relaxed Assignment Dependencies","date":"2025-02-27","arxiv_id":"2502.20190","repositories_listed":1,"syntology":null},{"url":"/paper/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/lexci-a-framework-for-reinforcement-learning","title":"LExCI: A Framework for Reinforcement Learning with Embedded Systems","date":"2023-12-05","arxiv_id":"2312.02739","repositories_listed":1,"syntology":null},{"url":"/paper/molopt-autonomous-molecular-geometry","title":"MolOpt: Autonomous Molecular Geometry Optimization using Multi-Agent Reinforcement Learning","date":"2023-08-24","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/corl-environment-creation-and-management","title":"CoRL: Environment Creation and Management Focused on System Integration","date":"2023-03-03","arxiv_id":"2303.02182","repositories_listed":1,"syntology":null},{"url":"/paper/raynet-a-simulation-platform-for-developing","title":"RayNet: A Simulation Platform for Developing Reinforcement Learning-Driven Network Protocols","date":"2023-02-09","arxiv_id":"2302.04519","repositories_listed":1,"syntology":null},{"url":"/paper/project-proposal-a-modular-reinforcement","title":"Project proposal: A modular reinforcement learning based automated theorem prover","date":"2022-09-06","arxiv_id":"2209.02562","repositories_listed":1,"syntology":null},{"url":"/paper/vmas-a-vectorized-multi-agent-simulator-for","title":"VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learning","date":"2022-07-07","arxiv_id":"2207.03530","repositories_listed":1,"syntology":null},{"url":"/paper/elegantrl-podracer-scalable-and-elastic","title":"ElegantRL-Podracer: Scalable and Elastic Library for Cloud-Native Deep Reinforcement Learning","date":"2021-12-11","arxiv_id":"2112.05923","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/godot-reinforcement-learning-agents","title":"Godot Reinforcement Learning Agents","date":"2021-12-07","arxiv_id":"2112.03636","repositories_listed":1,"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":1}},{"url":"/paper/malib-a-parallel-framework-for-population","title":"MALib: A Parallel Framework for Population-based Multi-agent Reinforcement Learning","date":"2021-06-05","arxiv_id":"2106.07551","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/distributed-reinforcement-learning-is-a","title":"RLlib Flow: Distributed Reinforcement Learning is a Dataflow Problem","date":"2020-11-25","arxiv_id":"2011.12719","repositories_listed":1,"syntology":null}],"syntology_records":4,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}