{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UNKTTGI2AZADNLV2WZOP5OZVAR","short_pith_number":"pith:UNKTTGI2","schema_version":"1.0","canonical_sha256":"a35539991a064036aebab65cfebb35046a8b61ffc893356affac4fbef84a9417","source":{"kind":"arxiv","id":"2109.11251","version":2},"attestation_state":"computed","paper":{"title":"Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Fanglei Sun, Jakub Grudzien Kuba, Jun Wang, Muning Wen, Ruiqing Chen, Yaodong Yang, Ying Wen","submitted_at":"2021-09-23T09:44:35Z","abstract_excerpt":"Trust region methods rigorously enabled reinforcement learning (RL) agents to learn monotonically improving policies, leading to superior performance on a variety of tasks. Unfortunately, when it comes to multi-agent reinforcement learning (MARL), the property of monotonic improvement may not simply apply; this is because agents, even in cooperative games, could have conflicting directions of policy updates. As a result, achieving a guaranteed improvement on the joint policy where each agent acts individually remains an open challenge. In this paper, we extend the theory of trust region learni"},"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":"2109.11251","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-09-23T09:44:35Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"150b987aaebbe03063426c3b44f20ed2c4b1b4513d70797fa315514da073fbac","abstract_canon_sha256":"f2cf818ad13653dc6bac2b368a5e37703b5846f63ddf87414848c05f10e30cbb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:07.684964Z","signature_b64":"Wip/YfSTOYBafD6IAV4FYNj6FhTjGsNuL3YHVDfpaqeOan6s8Qgh1aTWlHxIX5ZYlLnXxGzSMRGiDHKs97drBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a35539991a064036aebab65cfebb35046a8b61ffc893356affac4fbef84a9417","last_reissued_at":"2026-07-05T04:11:07.684511Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:07.684511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Fanglei Sun, Jakub Grudzien Kuba, Jun Wang, Muning Wen, Ruiqing Chen, Yaodong Yang, Ying Wen","submitted_at":"2021-09-23T09:44:35Z","abstract_excerpt":"Trust region methods rigorously enabled reinforcement learning (RL) agents to learn monotonically improving policies, leading to superior performance on a variety of tasks. Unfortunately, when it comes to multi-agent reinforcement learning (MARL), the property of monotonic improvement may not simply apply; this is because agents, even in cooperative games, could have conflicting directions of policy updates. As a result, achieving a guaranteed improvement on the joint policy where each agent acts individually remains an open challenge. In this paper, we extend the theory of trust region learni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.11251","kind":"arxiv","version":2},"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/2109.11251/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":"2109.11251","created_at":"2026-07-05T04:11:07.684558+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.11251v2","created_at":"2026-07-05T04:11:07.684558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.11251","created_at":"2026-07-05T04:11:07.684558+00:00"},{"alias_kind":"pith_short_12","alias_value":"UNKTTGI2AZAD","created_at":"2026-07-05T04:11:07.684558+00:00"},{"alias_kind":"pith_short_16","alias_value":"UNKTTGI2AZADNLV2","created_at":"2026-07-05T04:11:07.684558+00:00"},{"alias_kind":"pith_short_8","alias_value":"UNKTTGI2","created_at":"2026-07-05T04:11:07.684558+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25599","citing_title":"Reference-Free Heterogeneous Multi-Agent Reinforcement Learning for Grid-Friendly Tie-Line Power Shaping in Industrial Microgrids","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11284","citing_title":"Phi-Actor-Critic: Steering General-Sum Games to Pareto-Efficient Correlated Equilibria","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12655","citing_title":"Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning","ref_index":122,"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":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15207","citing_title":"TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2508.01049","citing_title":"Centralized Adaptive Sampling for Reliable Co-Training of Independent Multi-Agent Policies","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13554","citing_title":"Self-Supervised On-Policy Reinforcement Learning via Contrastive Proximal Policy Optimisation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05236","citing_title":"Topology-Driven Anti-Entanglement Control for Soft Robots","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UNKTTGI2AZADNLV2WZOP5OZVAR","json":"https://pith.science/pith/UNKTTGI2AZADNLV2WZOP5OZVAR.json","graph_json":"https://pith.science/api/pith-number/UNKTTGI2AZADNLV2WZOP5OZVAR/graph.json","events_json":"https://pith.science/api/pith-number/UNKTTGI2AZADNLV2WZOP5OZVAR/events.json","paper":"https://pith.science/paper/UNKTTGI2"},"agent_actions":{"view_html":"https://pith.science/pith/UNKTTGI2AZADNLV2WZOP5OZVAR","download_json":"https://pith.science/pith/UNKTTGI2AZADNLV2WZOP5OZVAR.json","view_paper":"https://pith.science/paper/UNKTTGI2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.11251&json=true","fetch_graph":"https://pith.science/api/pith-number/UNKTTGI2AZADNLV2WZOP5OZVAR/graph.json","fetch_events":"https://pith.science/api/pith-number/UNKTTGI2AZADNLV2WZOP5OZVAR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UNKTTGI2AZADNLV2WZOP5OZVAR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UNKTTGI2AZADNLV2WZOP5OZVAR/action/storage_attestation","attest_author":"https://pith.science/pith/UNKTTGI2AZADNLV2WZOP5OZVAR/action/author_attestation","sign_citation":"https://pith.science/pith/UNKTTGI2AZADNLV2WZOP5OZVAR/action/citation_signature","submit_replication":"https://pith.science/pith/UNKTTGI2AZADNLV2WZOP5OZVAR/action/replication_record"}},"created_at":"2026-07-05T04:11:07.684558+00:00","updated_at":"2026-07-05T04:11:07.684558+00:00"}