{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:IM2TDZG3XLP2LXBOC36PSZJVDX","short_pith_number":"pith:IM2TDZG3","schema_version":"1.0","canonical_sha256":"433531e4dbbadfa5dc2e16fcf965351ddff59354b1889ba7216f91bf4ebbcf75","source":{"kind":"arxiv","id":"1908.09453","version":6},"attestation_state":"computed","paper":{"title":"OpenSpiel: A Framework for Reinforcement Learning in Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.MA"],"primary_cat":"cs.LG","authors_text":"Bart De Vylder, Brennan Saeta, Daniel Hennes, David Ding, Dustin Morrill, Edward Hughes, Edward Lockhart, Finbarr Timbers, Ivo Danihelka, James Bradbury, J\\'anos Kram\\'ar, Jean-Baptiste Lespiau, Jonah Ryan-Davis, Julian Schrittwieser, Julien P\\'erolat, Karl Tuyls, Marc Lanctot, Matthew Lai, Paul Muller, Ryan Faulkner, Satyaki Upadhyay, Sebastian Borgeaud, Shayegan Omidshafiei, Sriram Srinivasan, Thomas Anthony, Timo Ewalds, Vinicius Zambaldi","submitted_at":"2019-08-26T03:31:35Z","abstract_excerpt":"OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games. OpenSpiel supports n-player (single- and multi- agent) zero-sum, cooperative and general-sum, one-shot and sequential, strictly turn-taking and simultaneous-move, perfect and imperfect information games, as well as traditional multiagent environments such as (partially- and fully- observable) grid worlds and social dilemmas. OpenSpiel also includes tools to analyze learning dynamics and other common evaluation metrics. This document serves both as an overview of"},"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":"1908.09453","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-26T03:31:35Z","cross_cats_sorted":["cs.AI","cs.GT","cs.MA"],"title_canon_sha256":"198d002c243fa8bbb291173f43f775b07a58b885382e3e65d46ed4d56114599c","abstract_canon_sha256":"4075d6d512fe9e42d0d8dd6bbe9618da81b14ea5dfc7ab5675a4d54059e2af40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:38:02.545627Z","signature_b64":"pOtK772mjwTinaBRux1zEsHHycYkP/s6od2+imzBhQS+qGsIIWQOhzgycDLtALGxUCOpCDZ5Y222QYx41n70Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"433531e4dbbadfa5dc2e16fcf965351ddff59354b1889ba7216f91bf4ebbcf75","last_reissued_at":"2026-07-05T01:38:02.545081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:38:02.545081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenSpiel: A Framework for Reinforcement Learning in Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.MA"],"primary_cat":"cs.LG","authors_text":"Bart De Vylder, Brennan Saeta, Daniel Hennes, David Ding, Dustin Morrill, Edward Hughes, Edward Lockhart, Finbarr Timbers, Ivo Danihelka, James Bradbury, J\\'anos Kram\\'ar, Jean-Baptiste Lespiau, Jonah Ryan-Davis, Julian Schrittwieser, Julien P\\'erolat, Karl Tuyls, Marc Lanctot, Matthew Lai, Paul Muller, Ryan Faulkner, Satyaki Upadhyay, Sebastian Borgeaud, Shayegan Omidshafiei, Sriram Srinivasan, Thomas Anthony, Timo Ewalds, Vinicius Zambaldi","submitted_at":"2019-08-26T03:31:35Z","abstract_excerpt":"OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games. OpenSpiel supports n-player (single- and multi- agent) zero-sum, cooperative and general-sum, one-shot and sequential, strictly turn-taking and simultaneous-move, perfect and imperfect information games, as well as traditional multiagent environments such as (partially- and fully- observable) grid worlds and social dilemmas. OpenSpiel also includes tools to analyze learning dynamics and other common evaluation metrics. This document serves both as an overview of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.09453","kind":"arxiv","version":6},"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/1908.09453/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":"1908.09453","created_at":"2026-07-05T01:38:02.545155+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.09453v6","created_at":"2026-07-05T01:38:02.545155+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.09453","created_at":"2026-07-05T01:38:02.545155+00:00"},{"alias_kind":"pith_short_12","alias_value":"IM2TDZG3XLP2","created_at":"2026-07-05T01:38:02.545155+00:00"},{"alias_kind":"pith_short_16","alias_value":"IM2TDZG3XLP2LXBO","created_at":"2026-07-05T01:38:02.545155+00:00"},{"alias_kind":"pith_short_8","alias_value":"IM2TDZG3","created_at":"2026-07-05T01:38:02.545155+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23995","citing_title":"EMAgnet: Parameter-Space EMA Regularization for Policy Gradient Self-Play in Large Games","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01498","citing_title":"Towards Learning Representations of Policies in Two-Player Zero-Sum Imperfect-Information Games","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06556","citing_title":"Robots Need More than VLA and World Models","ref_index":161,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31318","citing_title":"Generalized Intention Modeling in Multi-Agent Reinforcement Learning","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10325","citing_title":"Verifiable Process Rewards for Agentic Reasoning","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24375","citing_title":"Distilling Game Code World Model Generation into Lightweight Large Language Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2602.01665","citing_title":"TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16315","citing_title":"A Structural Threshold in Decision Capacity Governs Collapse in Self-Play Reinforcement Learning","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19235","citing_title":"GAE Falls Short in Imperfect-Information Self-Play Reinforcement Learning","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19928","citing_title":"Real-Time Parallel Counterfactual Regret Minimization","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2506.02387","citing_title":"VS-Bench: Evaluating VLMs for Strategic Abilities in Multi-Agent Environments","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2510.18183","citing_title":"NashPG: A Policy Gradient Method with Iteratively Refined Regularization for Finding Nash Equilibria","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2511.03724","citing_title":"Outbidding and Outbluffing Elite Humans: Mastering Liar's Poker via Self-Play and Reinforcement Learning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27162","citing_title":"A High-Throughput Compute-Efficient POMDP Hide-And-Seek-Engine (HASE) for Multi-Agent Operations","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10900","citing_title":"Effective, Efficient, and General Information Abstraction for Imperfect-Information Extensive-Form Games","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10325","citing_title":"Verifiable Process Rewards for Agentic Reasoning","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25796","citing_title":"StratFormer: Adaptive Opponent Modeling and Exploitation in Imperfect-Information Games","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10252","citing_title":"A Dual-Positive Monotone Parameterization for Multi-Segment Bids and a Validity Assessment Framework for Reinforcement Learning Agent-based Simulation of Electricity Markets","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02063","citing_title":"Coopetition-Gym v1: A Formally Grounded Platform for Mixed-Motive Multi-Agent Reinforcement Learning under Strategic Coopetition","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IM2TDZG3XLP2LXBOC36PSZJVDX","json":"https://pith.science/pith/IM2TDZG3XLP2LXBOC36PSZJVDX.json","graph_json":"https://pith.science/api/pith-number/IM2TDZG3XLP2LXBOC36PSZJVDX/graph.json","events_json":"https://pith.science/api/pith-number/IM2TDZG3XLP2LXBOC36PSZJVDX/events.json","paper":"https://pith.science/paper/IM2TDZG3"},"agent_actions":{"view_html":"https://pith.science/pith/IM2TDZG3XLP2LXBOC36PSZJVDX","download_json":"https://pith.science/pith/IM2TDZG3XLP2LXBOC36PSZJVDX.json","view_paper":"https://pith.science/paper/IM2TDZG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.09453&json=true","fetch_graph":"https://pith.science/api/pith-number/IM2TDZG3XLP2LXBOC36PSZJVDX/graph.json","fetch_events":"https://pith.science/api/pith-number/IM2TDZG3XLP2LXBOC36PSZJVDX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IM2TDZG3XLP2LXBOC36PSZJVDX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IM2TDZG3XLP2LXBOC36PSZJVDX/action/storage_attestation","attest_author":"https://pith.science/pith/IM2TDZG3XLP2LXBOC36PSZJVDX/action/author_attestation","sign_citation":"https://pith.science/pith/IM2TDZG3XLP2LXBOC36PSZJVDX/action/citation_signature","submit_replication":"https://pith.science/pith/IM2TDZG3XLP2LXBOC36PSZJVDX/action/replication_record"}},"created_at":"2026-07-05T01:38:02.545155+00:00","updated_at":"2026-07-05T01:38:02.545155+00:00"}