{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:E3P4PPIQD5KDUJBB5YJ223F6LL","short_pith_number":"pith:E3P4PPIQ","canonical_record":{"source":{"id":"2105.03363","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-07T16:20:22Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"6ce21e8e0ca46f9f1a3ffb822c81acceebb97c296d10bf40a57e73ec8a1d2188","abstract_canon_sha256":"ed91dd56cbc3334fa29f7673152305587825ae65719ffe0aafd2ec60dd21e8b4"},"schema_version":"1.0"},"canonical_sha256":"26dfc7bd101f543a2421ee13ad6cbe5afac8542477690bc1555ddf458d87eb4e","source":{"kind":"arxiv","id":"2105.03363","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:E3P4PPIQD5KDUJBB5YJ223F6LL","target":"record","payload":{"canonical_record":{"source":{"id":"2105.03363","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-07T16:20:22Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"6ce21e8e0ca46f9f1a3ffb822c81acceebb97c296d10bf40a57e73ec8a1d2188","abstract_canon_sha256":"ed91dd56cbc3334fa29f7673152305587825ae65719ffe0aafd2ec60dd21e8b4"},"schema_version":"1.0"},"canonical_sha256":"26dfc7bd101f543a2421ee13ad6cbe5afac8542477690bc1555ddf458d87eb4e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:58.426207Z","signature_b64":"vtPFLVRAATsSbW1OwUyKj407PsCiWsVcT1NPbWdP+LsrlInCslFED5M9eor9H/QXYUDa5ri7nN2Z7w4tiCX5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26dfc7bd101f543a2421ee13ad6cbe5afac8542477690bc1555ddf458d87eb4e","last_reissued_at":"2026-07-05T04:05:58.425790Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:58.425790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.03363","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:05:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4aqbLj3yRde9YMTOI53Cgtir36yuxFifTiGEGX5QMPowKToWssxEPue/QvU3dVw62Ts3xWosBU6P6G4NQyLtBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:48:02.082276Z"},"content_sha256":"4471354cccb36c23bcba34e66c7c503f5a68fec88c3b0cebea0f93eba5f80006","schema_version":"1.0","event_id":"sha256:4471354cccb36c23bcba34e66c7c503f5a68fec88c3b0cebea0f93eba5f80006"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:E3P4PPIQD5KDUJBB5YJ223F6LL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model-based Multi-agent Policy Optimization with Adaptive Opponent-wise Rollouts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Jian Shen, Ming Zhou, Weinan Zhang, Xihuai Wang","submitted_at":"2021-05-07T16:20:22Z","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,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.03363","kind":"arxiv","version":3},"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/2105.03363/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":"2026-07-05T04:05:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OGnAkm3BPlWZw5B0nqY1SbKiDDrSkfy5jbbhakW+InB0yNOZf/UHg6cPoeqLsjuL1w3UiqnOHSenBSuENpLmDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:48:02.082796Z"},"content_sha256":"d88ce45c3ed2efe3721e22758c93dfacdcb8f7222606db6f8069f49686e85f91","schema_version":"1.0","event_id":"sha256:d88ce45c3ed2efe3721e22758c93dfacdcb8f7222606db6f8069f49686e85f91"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E3P4PPIQD5KDUJBB5YJ223F6LL/bundle.json","state_url":"https://pith.science/pith/E3P4PPIQD5KDUJBB5YJ223F6LL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E3P4PPIQD5KDUJBB5YJ223F6LL/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":"2026-08-03T16:48:02Z","links":{"resolver":"https://pith.science/pith/E3P4PPIQD5KDUJBB5YJ223F6LL","bundle":"https://pith.science/pith/E3P4PPIQD5KDUJBB5YJ223F6LL/bundle.json","state":"https://pith.science/pith/E3P4PPIQD5KDUJBB5YJ223F6LL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E3P4PPIQD5KDUJBB5YJ223F6LL/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y2zUmUO2DcJwEra8iNuwqhxcyW207xnTGoElpllzOm695LGIbaSQGl814X/xnHdP/OGQNzLp21Zsq7Pl5vMeDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:48:02.086461Z","bundle_sha256":"c9c969597f8fde7b6bcc11dc0dfd02c400502625c3809143dd4a1e7e3e035185"}}