{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:E3P4PPIQD5KDUJBB5YJ223F6LL","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":"ed91dd56cbc3334fa29f7673152305587825ae65719ffe0aafd2ec60dd21e8b4","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-07T16:20:22Z","title_canon_sha256":"6ce21e8e0ca46f9f1a3ffb822c81acceebb97c296d10bf40a57e73ec8a1d2188"},"schema_version":"1.0","source":{"id":"2105.03363","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.03363","created_at":"2026-07-05T04:05:58Z"},{"alias_kind":"arxiv_version","alias_value":"2105.03363v3","created_at":"2026-07-05T04:05:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.03363","created_at":"2026-07-05T04:05:58Z"},{"alias_kind":"pith_short_12","alias_value":"E3P4PPIQD5KD","created_at":"2026-07-05T04:05:58Z"},{"alias_kind":"pith_short_16","alias_value":"E3P4PPIQD5KDUJBB","created_at":"2026-07-05T04:05:58Z"},{"alias_kind":"pith_short_8","alias_value":"E3P4PPIQ","created_at":"2026-07-05T04:05:58Z"}],"graph_snapshots":[{"event_id":"sha256:d88ce45c3ed2efe3721e22758c93dfacdcb8f7222606db6f8069f49686e85f91","target":"graph","created_at":"2026-07-05T04:05:58Z","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/2105.03363/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper investigates the model-based methods in multi-agent reinforcement learning (MARL). We specify the dynamics sample complexity and the opponent sample complexity in MARL, and conduct a theoretic analysis of return discrepancy upper bound. To reduce the upper bound with the intention of low sample complexity during the whole learning process, we propose a novel decentralized model-based MARL method, named Adaptive Opponent-wise Rollout Policy Optimization (AORPO). In AORPO, each agent builds its multi-agent environment model, consisting of a dynamics model and multiple opponent models,","authors_text":"Jian Shen, Ming Zhou, Weinan Zhang, Xihuai Wang","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-07T16:20:22Z","title":"Model-based Multi-agent Policy Optimization with Adaptive Opponent-wise Rollouts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.03363","kind":"arxiv","version":3},"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":"sha256:4471354cccb36c23bcba34e66c7c503f5a68fec88c3b0cebea0f93eba5f80006","target":"record","created_at":"2026-07-05T04:05:58Z","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":"ed91dd56cbc3334fa29f7673152305587825ae65719ffe0aafd2ec60dd21e8b4","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-07T16:20:22Z","title_canon_sha256":"6ce21e8e0ca46f9f1a3ffb822c81acceebb97c296d10bf40a57e73ec8a1d2188"},"schema_version":"1.0","source":{"id":"2105.03363","kind":"arxiv","version":3}},"canonical_sha256":"26dfc7bd101f543a2421ee13ad6cbe5afac8542477690bc1555ddf458d87eb4e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26dfc7bd101f543a2421ee13ad6cbe5afac8542477690bc1555ddf458d87eb4e","first_computed_at":"2026-07-05T04:05:58.425790Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:05:58.425790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vtPFLVRAATsSbW1OwUyKj407PsCiWsVcT1NPbWdP+LsrlInCslFED5M9eor9H/QXYUDa5ri7nN2Z7w4tiCX5Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:05:58.426207Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.03363","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4471354cccb36c23bcba34e66c7c503f5a68fec88c3b0cebea0f93eba5f80006","sha256:d88ce45c3ed2efe3721e22758c93dfacdcb8f7222606db6f8069f49686e85f91"],"state_sha256":"d98f5d2e142c51179e0ecaa38418728b17ccd88e3e2b3cffbc213439bc2c8ae8"}