{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:QYSKLZTX43ZBBRRR26DFGLFKWG","short_pith_number":"pith:QYSKLZTX","schema_version":"1.0","canonical_sha256":"8624a5e677e6f210c631d786532caab184fd952f3f8ea1deaf845a89d7ed9ff7","source":{"kind":"arxiv","id":"1606.01540","version":1},"attestation_state":"computed","paper":{"title":"OpenAI Gym","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A toolkit supplies benchmark problems for reinforcement learning through a shared interface along with a website for comparing algorithm results.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Greg Brockman, Jie Tang, John Schulman, Jonas Schneider, Ludwig Pettersson, Vicki Cheung, Wojciech Zaremba","submitted_at":"2016-06-05T17:54:48Z","abstract_excerpt":"OpenAI Gym is a toolkit for reinforcement learning research. It includes a growing collection of benchmark problems that expose a common interface, and a website where people can share their results and compare the performance of algorithms. This whitepaper discusses the components of OpenAI Gym and the design decisions that went into the software."},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":false},"canonical_record":{"source":{"id":"1606.01540","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-06-05T17:54:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"56fea31d271806fa816a874361b3e508e0ba23bb9f3f10c323c9ecaa11c9b938","abstract_canon_sha256":"31f6d5bdbc216acf9f4c1ab7bdce369476e0f3fbf35079d0bf9aa3eb4a8daf24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T21:03:34.074023Z","signature_b64":"b2sMPH4udiquD6uKXIIV0Oq+ABNXHBcDjt50IJfN7V/wXiofe+OLWBNX9YW2Rgc3BLI4ZxantgYgWbQl60t2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8624a5e677e6f210c631d786532caab184fd952f3f8ea1deaf845a89d7ed9ff7","last_reissued_at":"2026-07-04T21:03:34.073509Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T21:03:34.073509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenAI Gym","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A toolkit supplies benchmark problems for reinforcement learning through a shared interface along with a website for comparing algorithm results.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Greg Brockman, Jie Tang, John Schulman, Jonas Schneider, Ludwig Pettersson, Vicki Cheung, Wojciech Zaremba","submitted_at":"2016-06-05T17:54:48Z","abstract_excerpt":"OpenAI Gym is a toolkit for reinforcement learning research. It includes a growing collection of benchmark problems that expose a common interface, and a website where people can share their results and compare the performance of algorithms. This whitepaper discusses the components of OpenAI Gym and the design decisions that went into the software."},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"OpenAI Gym is a toolkit for reinforcement learning research. It includes a growing collection of benchmark problems that expose a common interface, and a website where people can share their results and compare the performance of algorithms.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a common interface plus public result sharing will be sufficient to drive meaningful progress and fair comparisons, without addressing whether the chosen environments adequately represent real-world complexity or diversity of tasks.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"OpenAI Gym introduces a common interface for reinforcement learning environments and a results-sharing website to enable consistent algorithm comparisons.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A toolkit supplies benchmark problems for reinforcement learning through a shared interface along with a website for comparing algorithm results.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b4e9a32b03e160a11aca312a59d6b682c72d3c4dbeae247e8c5f59635734a29b"},"source":{"id":"1606.01540","kind":"arxiv","version":1},"verdict":{"id":"0d263c97-fdee-4aa7-b588-f82c7144cd12","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T19:44:10.330352Z","strongest_claim":"OpenAI Gym is a toolkit for reinforcement learning research. It includes a growing collection of benchmark problems that expose a common interface, and a website where people can share their results and compare the performance of algorithms.","one_line_summary":"OpenAI Gym introduces a common interface for reinforcement learning environments and a results-sharing website to enable consistent algorithm comparisons.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a common interface plus public result sharing will be sufficient to drive meaningful progress and fair comparisons, without addressing whether the chosen environments adequately represent real-world complexity or diversity of tasks.","pith_extraction_headline":"A toolkit supplies benchmark problems for reinforcement learning through a shared interface along with a website for comparing algorithm results."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1606.01540/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":15,"sample":[{"doi":"","year":1995,"title":"Dynamic programming and optimal control","work_id":"b2ea3f9f-2ebe-41e2-8330-a140e7bf8c6b","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2015,"title":"V . Mnih, K. Kavukcuoglu, D. Silver, A. A. Rusu, J. Veness, M. G. Bellemare, A. Graves, M. Riedmiller, A. K. Fidjeland, G. Ostrovski, S. Petersen, Sadik Beattie, C., Antonoglou A., H. I., King, D. Kum","work_id":"b1509e5c-b3da-4ffa-9f09-45c396463a06","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2015,"title":"J. Schulman, S. Levine, P. Abbeel, M. I. Jordan, and P. Moritz. Trust region policy optimization. In ICML, pages 1889–1897, 2015","work_id":"041d632c-7466-47c8-ad82-9b9a540abe13","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"Asynchronous Methods for Deep Reinforcement Learning","work_id":"b54058f9-0b3b-46ae-a9a0-f22748625e2a","ref_index":4,"cited_arxiv_id":"1602.01783","is_internal_anchor":false},{"doi":"","year":2013,"title":"M. G. Bellemare, Y . Naddaf, J. Veness, and M. Bowling. The Arcade Learning Environment: An evaluation platform for general agents. J. Artif. Intell. Res., 47:253–279, 2013","work_id":"e9360171-a564-4345-b474-6d1665449d8d","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":15,"snapshot_sha256":"7cb6aa4d9ea2bb97016e0b2b108bc06c172f7da556469e1c6ace24c4574aa3d2","internal_anchors":1},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1606.01540","created_at":"2026-07-04T21:03:34.073570+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.01540v1","created_at":"2026-07-04T21:03:34.073570+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.01540","created_at":"2026-07-04T21:03:34.073570+00:00"},{"alias_kind":"pith_short_12","alias_value":"QYSKLZTX43ZB","created_at":"2026-07-04T21:03:34.073570+00:00"},{"alias_kind":"pith_short_16","alias_value":"QYSKLZTX43ZBBRRR","created_at":"2026-07-04T21:03:34.073570+00:00"},{"alias_kind":"pith_short_8","alias_value":"QYSKLZTX","created_at":"2026-07-04T21:03:34.073570+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":162,"internal_anchor_count":162,"sample":[{"citing_arxiv_id":"2607.07753","citing_title":"A Transdiagnostic Space of Disorder Like Phenotypes in Reinforcement Learning Agents","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2607.07029","citing_title":"Gimitest: A Comprehensive Tool for Testing Reinforcement Learning Policies","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26048","citing_title":"Deep Reinforcement Learning-Enhanced Event-Triggered Data-Driven Predictive Control for a 3D Cable-Driven Soft Robotic Arm","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24991","citing_title":"Solving Markov Decision Processes with Future Information via MPC","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26327","citing_title":"EVOM: Agentic Meta-Evolution of Actor-Critic Architectures for Reinforcement Learning","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23115","citing_title":"Mass Conservation as an Inductive Bias for Self-Organized Criticality in NCA Reservoirs","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22509","citing_title":"Imagine to Ensure Safety in Hierarchical Reinforcement Learning","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22385","citing_title":"MetaPS: Adaptive Programmatic Strategy Selection for Market Agents","ref_index":186,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21891","citing_title":"Learning the ARTS of Search for Automated Discovery","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21587","citing_title":"FAST: A Framework for Aligned Sampling and Training in Parallel Reinforcement Learning for Autonomous Driving","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21086","citing_title":"ReFPO: Reflow Regularization for Flow Matching Policy Gradients","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20817","citing_title":"Provably Sub-Linear Two-Timescale NeuroEvolution with Online Plasticity","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2606.19980","citing_title":"ENPIRE: Agentic Robot Policy Self-Improvement in the Real World","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20376","citing_title":"CRAX: Fast Safe Reinforcement Learning Benchmarking","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2606.19721","citing_title":"OnDeFog: Online Decision Transformer under Frame Dropping","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18963","citing_title":"Online Reward-Punishment Learning from Fixed-Channel Perceptual Event Streams without Environment Rewards","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2606.17511","citing_title":"MagicSim: A Unified Infrastructure for Executable Embodied Interaction","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2607.02490","citing_title":"Visually Grounded Self-Reflection for Vision-Language Models via Reinforcement Learning","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2606.12191","citing_title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2606.11770","citing_title":"SVoT: State-aware Visualization-of-Thought for Spatial Reasoning via Reinforcement Learning","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2606.10891","citing_title":"Bilinear gating of motor primitives: a principle linking dendritic computation to rapid goal-directed adaptation","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2606.09236","citing_title":"Self-Paced Curriculum Reinforcement Learning for Autonomous Superbike Racing in Simulation","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2606.08729","citing_title":"IR-SIM: A Lightweight Skill-Native Simulator for Navigation, Learning, and Benchmarking","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2606.08168","citing_title":"Closing the Sim-to-Real Gap: An Evaluation Framework for Autonomous Cyber Defense Configuration of Commercial EDR","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2606.08278","citing_title":"SIMPLE: Simulation-Based Policy Learning and Evaluation for Humanoid Loco-manipulation","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QYSKLZTX43ZBBRRR26DFGLFKWG","json":"https://pith.science/pith/QYSKLZTX43ZBBRRR26DFGLFKWG.json","graph_json":"https://pith.science/api/pith-number/QYSKLZTX43ZBBRRR26DFGLFKWG/graph.json","events_json":"https://pith.science/api/pith-number/QYSKLZTX43ZBBRRR26DFGLFKWG/events.json","paper":"https://pith.science/paper/QYSKLZTX"},"agent_actions":{"view_html":"https://pith.science/pith/QYSKLZTX43ZBBRRR26DFGLFKWG","download_json":"https://pith.science/pith/QYSKLZTX43ZBBRRR26DFGLFKWG.json","view_paper":"https://pith.science/paper/QYSKLZTX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.01540&json=true","fetch_graph":"https://pith.science/api/pith-number/QYSKLZTX43ZBBRRR26DFGLFKWG/graph.json","fetch_events":"https://pith.science/api/pith-number/QYSKLZTX43ZBBRRR26DFGLFKWG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QYSKLZTX43ZBBRRR26DFGLFKWG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QYSKLZTX43ZBBRRR26DFGLFKWG/action/storage_attestation","attest_author":"https://pith.science/pith/QYSKLZTX43ZBBRRR26DFGLFKWG/action/author_attestation","sign_citation":"https://pith.science/pith/QYSKLZTX43ZBBRRR26DFGLFKWG/action/citation_signature","submit_replication":"https://pith.science/pith/QYSKLZTX43ZBBRRR26DFGLFKWG/action/replication_record"}},"created_at":"2026-07-04T21:03:34.073570+00:00","updated_at":"2026-07-04T21:03:34.073570+00:00"}