{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:UNKTTGI2AZADNLV2WZOP5OZVAR","short_pith_number":"pith:UNKTTGI2","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"},"canonical_sha256":"a35539991a064036aebab65cfebb35046a8b61ffc893356affac4fbef84a9417","source":{"kind":"arxiv","id":"2109.11251","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.11251","created_at":"2026-07-05T04:11:07Z"},{"alias_kind":"arxiv_version","alias_value":"2109.11251v2","created_at":"2026-07-05T04:11:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.11251","created_at":"2026-07-05T04:11:07Z"},{"alias_kind":"pith_short_12","alias_value":"UNKTTGI2AZAD","created_at":"2026-07-05T04:11:07Z"},{"alias_kind":"pith_short_16","alias_value":"UNKTTGI2AZADNLV2","created_at":"2026-07-05T04:11:07Z"},{"alias_kind":"pith_short_8","alias_value":"UNKTTGI2","created_at":"2026-07-05T04:11:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:UNKTTGI2AZADNLV2WZOP5OZVAR","target":"record","payload":{"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"},"canonical_sha256":"a35539991a064036aebab65cfebb35046a8b61ffc893356affac4fbef84a9417","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"},"source_kind":"arxiv","source_id":"2109.11251","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:11:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S9ztOdAD3D0O7yKjAfnuXB1kjdemKnQvH6IJgU/tC5aAncDh2eSPC9HMfQyyG5DbZ0dkWrUgqrpb8C/4ulStDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:21:17.396712Z"},"content_sha256":"c35759819ff9e7f5ebb337814ac8440f0fd528c1e4efb8202f6f17c85ae1fc2e","schema_version":"1.0","event_id":"sha256:c35759819ff9e7f5ebb337814ac8440f0fd528c1e4efb8202f6f17c85ae1fc2e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:UNKTTGI2AZADNLV2WZOP5OZVAR","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:11:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c2JdKUJ9binlhY7DQqCkSx8+9LnegXu+rpA6uraxREAixIFqbEmKvP79iap4yJ0RzHy2cVCL4LWG3QAWWbmDCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:21:17.397208Z"},"content_sha256":"83d73f838a9c1fb022675ef51ae31efb5b6365ef7c725bec15eeabd7bac0b3aa","schema_version":"1.0","event_id":"sha256:83d73f838a9c1fb022675ef51ae31efb5b6365ef7c725bec15eeabd7bac0b3aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UNKTTGI2AZADNLV2WZOP5OZVAR/bundle.json","state_url":"https://pith.science/pith/UNKTTGI2AZADNLV2WZOP5OZVAR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UNKTTGI2AZADNLV2WZOP5OZVAR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T19:21:17Z","links":{"resolver":"https://pith.science/pith/UNKTTGI2AZADNLV2WZOP5OZVAR","bundle":"https://pith.science/pith/UNKTTGI2AZADNLV2WZOP5OZVAR/bundle.json","state":"https://pith.science/pith/UNKTTGI2AZADNLV2WZOP5OZVAR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UNKTTGI2AZADNLV2WZOP5OZVAR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:UNKTTGI2AZADNLV2WZOP5OZVAR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f2cf818ad13653dc6bac2b368a5e37703b5846f63ddf87414848c05f10e30cbb","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-09-23T09:44:35Z","title_canon_sha256":"150b987aaebbe03063426c3b44f20ed2c4b1b4513d70797fa315514da073fbac"},"schema_version":"1.0","source":{"id":"2109.11251","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.11251","created_at":"2026-07-05T04:11:07Z"},{"alias_kind":"arxiv_version","alias_value":"2109.11251v2","created_at":"2026-07-05T04:11:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.11251","created_at":"2026-07-05T04:11:07Z"},{"alias_kind":"pith_short_12","alias_value":"UNKTTGI2AZAD","created_at":"2026-07-05T04:11:07Z"},{"alias_kind":"pith_short_16","alias_value":"UNKTTGI2AZADNLV2","created_at":"2026-07-05T04:11:07Z"},{"alias_kind":"pith_short_8","alias_value":"UNKTTGI2","created_at":"2026-07-05T04:11:07Z"}],"graph_snapshots":[{"event_id":"sha256:83d73f838a9c1fb022675ef51ae31efb5b6365ef7c725bec15eeabd7bac0b3aa","target":"graph","created_at":"2026-07-05T04:11:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2109.11251/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Fanglei Sun, Jakub Grudzien Kuba, Jun Wang, Muning Wen, Ruiqing Chen, Yaodong Yang, Ying Wen","cross_cats":["cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-09-23T09:44:35Z","title":"Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.11251","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c35759819ff9e7f5ebb337814ac8440f0fd528c1e4efb8202f6f17c85ae1fc2e","target":"record","created_at":"2026-07-05T04:11:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f2cf818ad13653dc6bac2b368a5e37703b5846f63ddf87414848c05f10e30cbb","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-09-23T09:44:35Z","title_canon_sha256":"150b987aaebbe03063426c3b44f20ed2c4b1b4513d70797fa315514da073fbac"},"schema_version":"1.0","source":{"id":"2109.11251","kind":"arxiv","version":2}},"canonical_sha256":"a35539991a064036aebab65cfebb35046a8b61ffc893356affac4fbef84a9417","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a35539991a064036aebab65cfebb35046a8b61ffc893356affac4fbef84a9417","first_computed_at":"2026-07-05T04:11:07.684511Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:11:07.684511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Wip/YfSTOYBafD6IAV4FYNj6FhTjGsNuL3YHVDfpaqeOan6s8Qgh1aTWlHxIX5ZYlLnXxGzSMRGiDHKs97drBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:11:07.684964Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.11251","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c35759819ff9e7f5ebb337814ac8440f0fd528c1e4efb8202f6f17c85ae1fc2e","sha256:83d73f838a9c1fb022675ef51ae31efb5b6365ef7c725bec15eeabd7bac0b3aa"],"state_sha256":"b26499a40d81a3e5eb7ebf4d45551cba6747b4a8e318cb0866be8a03177790bc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5lgS/MLRwyXfdB9T+wm/Fh8nnF6eYXAyjNj7YRQlN9RmcDe66MlCjzHZJrTmTFNThGx3pliw0xdz1112UnnuCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:21:17.400936Z","bundle_sha256":"c9a19058e76d6754cf12a9103f0c912d471c88a3e798f23dc61e8ebc7ffe87f5"}}