{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:M5PWVVLO7GZF5NQ24ZHA5GDRBN","short_pith_number":"pith:M5PWVVLO","schema_version":"1.0","canonical_sha256":"675f6ad56ef9b25eb61ae64e0e98710b4f04b5c04e9c3f12e43202d6661c88ec","source":{"kind":"arxiv","id":"2009.14471","version":7},"attestation_state":"computed","paper":{"title":"PettingZoo: Gym for Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ananth Hari, Benjamin Black, Caroline Horsch, Clemens Dieffendahl, J. K. Terry, Luis Santos, Mario Jayakumar, Nathaniel Grammel, Niall L. Williams, Praveen Ravi, Rodrigo Perez, Ryan Sullivan, Yashas Lokesh","submitted_at":"2020-09-30T06:42:09Z","abstract_excerpt":"This paper introduces the PettingZoo library and the accompanying Agent Environment Cycle (\"AEC\") games model. PettingZoo is a library of diverse sets of multi-agent environments with a universal, elegant Python API. PettingZoo was developed with the goal of accelerating research in Multi-Agent Reinforcement Learning (\"MARL\"), by making work more interchangeable, accessible and reproducible akin to what OpenAI's Gym library did for single-agent reinforcement learning. PettingZoo's API, while inheriting many features of Gym, is unique amongst MARL APIs in that it's based around the novel AEC ga"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2009.14471","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-30T06:42:09Z","cross_cats_sorted":["cs.MA","stat.ML"],"title_canon_sha256":"2f6aef7940304e6101de48af5619ab6b6012e35225f9b00b22703f2f85bc72fc","abstract_canon_sha256":"384cf58613d939e3953378eacee098cbff39fe527c547404ba14503bfcfe738c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:31:54.204019Z","signature_b64":"23ttTMqlicjgfICxYUMHRnFfElNv9DDwU+vect9oaRgFnqf02rKdvc2hNqicOore00dXe3lbtyBMZExLnhs/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"675f6ad56ef9b25eb61ae64e0e98710b4f04b5c04e9c3f12e43202d6661c88ec","last_reissued_at":"2026-07-05T03:31:54.203475Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:31:54.203475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PettingZoo: Gym for Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ananth Hari, Benjamin Black, Caroline Horsch, Clemens Dieffendahl, J. K. Terry, Luis Santos, Mario Jayakumar, Nathaniel Grammel, Niall L. Williams, Praveen Ravi, Rodrigo Perez, Ryan Sullivan, Yashas Lokesh","submitted_at":"2020-09-30T06:42:09Z","abstract_excerpt":"This paper introduces the PettingZoo library and the accompanying Agent Environment Cycle (\"AEC\") games model. PettingZoo is a library of diverse sets of multi-agent environments with a universal, elegant Python API. PettingZoo was developed with the goal of accelerating research in Multi-Agent Reinforcement Learning (\"MARL\"), by making work more interchangeable, accessible and reproducible akin to what OpenAI's Gym library did for single-agent reinforcement learning. PettingZoo's API, while inheriting many features of Gym, is unique amongst MARL APIs in that it's based around the novel AEC ga"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.14471","kind":"arxiv","version":7},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2009.14471/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"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":"2009.14471","created_at":"2026-07-05T03:31:54.203536+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.14471v7","created_at":"2026-07-05T03:31:54.203536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.14471","created_at":"2026-07-05T03:31:54.203536+00:00"},{"alias_kind":"pith_short_12","alias_value":"M5PWVVLO7GZF","created_at":"2026-07-05T03:31:54.203536+00:00"},{"alias_kind":"pith_short_16","alias_value":"M5PWVVLO7GZF5NQ2","created_at":"2026-07-05T03:31:54.203536+00:00"},{"alias_kind":"pith_short_8","alias_value":"M5PWVVLO","created_at":"2026-07-05T03:31:54.203536+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06227","citing_title":"Reward hacking in physical reinforcement learning revealed by turbulent drag reduction","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05021","citing_title":"Enhancing the MADDPG Algorithm for Multi-Agent Learning via Action Inference and Importance Sampling","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2603.06977","citing_title":"NePPO: Near-Potential Policy Optimization for General-Sum Multi-Agent Reinforcement Learning","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09434","citing_title":"Physics-guided surrogate learning enables zero-shot control of turbulent wings","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18190","citing_title":"Scalable Neighborhood-Based Multi-Agent Actor-Critic","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M5PWVVLO7GZF5NQ24ZHA5GDRBN","json":"https://pith.science/pith/M5PWVVLO7GZF5NQ24ZHA5GDRBN.json","graph_json":"https://pith.science/api/pith-number/M5PWVVLO7GZF5NQ24ZHA5GDRBN/graph.json","events_json":"https://pith.science/api/pith-number/M5PWVVLO7GZF5NQ24ZHA5GDRBN/events.json","paper":"https://pith.science/paper/M5PWVVLO"},"agent_actions":{"view_html":"https://pith.science/pith/M5PWVVLO7GZF5NQ24ZHA5GDRBN","download_json":"https://pith.science/pith/M5PWVVLO7GZF5NQ24ZHA5GDRBN.json","view_paper":"https://pith.science/paper/M5PWVVLO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.14471&json=true","fetch_graph":"https://pith.science/api/pith-number/M5PWVVLO7GZF5NQ24ZHA5GDRBN/graph.json","fetch_events":"https://pith.science/api/pith-number/M5PWVVLO7GZF5NQ24ZHA5GDRBN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M5PWVVLO7GZF5NQ24ZHA5GDRBN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M5PWVVLO7GZF5NQ24ZHA5GDRBN/action/storage_attestation","attest_author":"https://pith.science/pith/M5PWVVLO7GZF5NQ24ZHA5GDRBN/action/author_attestation","sign_citation":"https://pith.science/pith/M5PWVVLO7GZF5NQ24ZHA5GDRBN/action/citation_signature","submit_replication":"https://pith.science/pith/M5PWVVLO7GZF5NQ24ZHA5GDRBN/action/replication_record"}},"created_at":"2026-07-05T03:31:54.203536+00:00","updated_at":"2026-07-05T03:31:54.203536+00:00"}