{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:K7FXSQOFV22P6TEV36EP2JHUFT","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":"8dc2a8b154bff97ce76168f5eed22124b20be6738c49b58e88ab3a02ec628be6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-10T01:58:28Z","title_canon_sha256":"5f5a352818b02bc02d526ad33d20b88a565f404997b68810ba8a6699bf56517e"},"schema_version":"1.0","source":{"id":"2102.06042","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.06042","created_at":"2026-07-05T02:14:37Z"},{"alias_kind":"arxiv_version","alias_value":"2102.06042v1","created_at":"2026-07-05T02:14:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.06042","created_at":"2026-07-05T02:14:37Z"},{"alias_kind":"pith_short_12","alias_value":"K7FXSQOFV22P","created_at":"2026-07-05T02:14:37Z"},{"alias_kind":"pith_short_16","alias_value":"K7FXSQOFV22P6TEV","created_at":"2026-07-05T02:14:37Z"},{"alias_kind":"pith_short_8","alias_value":"K7FXSQOF","created_at":"2026-07-05T02:14:37Z"}],"graph_snapshots":[{"event_id":"sha256:8d71062d3ecf55e1a5877833343c113515c80ed5a182be54b2e3ca82f2fc898c","target":"graph","created_at":"2026-07-05T02:14:37Z","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/2102.06042/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Value-based methods of multi-agent reinforcement learning (MARL), especially the value decomposition methods, have been demonstrated on a range of challenging cooperative tasks. However, current methods pay little attention to the interaction between agents, which is essential to teamwork in games or real life. This limits the efficiency of value-based MARL algorithms in the two aspects: collaborative exploration and value function estimation. In this paper, we propose a novel cooperative MARL algorithm named as interactive actor-critic~(IAC), which models the interaction of agents from the pe","authors_text":"Chenghao Li, Qianchuan Zhao, Xiaoteng Ma, Yang jun, Yiqin Yang, Yiwen Lu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-10T01:58:28Z","title":"Modeling the Interaction between Agents in Cooperative Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.06042","kind":"arxiv","version":1},"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":"sha256:96a7bb75468b157906059a7142f6e12bfdf60e5c88c81ccfb29fa3b918357d53","target":"record","created_at":"2026-07-05T02:14:37Z","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":"8dc2a8b154bff97ce76168f5eed22124b20be6738c49b58e88ab3a02ec628be6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-10T01:58:28Z","title_canon_sha256":"5f5a352818b02bc02d526ad33d20b88a565f404997b68810ba8a6699bf56517e"},"schema_version":"1.0","source":{"id":"2102.06042","kind":"arxiv","version":1}},"canonical_sha256":"57cb7941c5aeb4ff4c95df88fd24f42ce74fefd78cca7e2fcd59952e73a7d26b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57cb7941c5aeb4ff4c95df88fd24f42ce74fefd78cca7e2fcd59952e73a7d26b","first_computed_at":"2026-07-05T02:14:37.341850Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:14:37.341850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DO4IpZwUd5j1mbSpbw9eDrws1wx/40rK+drXrqNi4y/5wAQPK5F8YfnUHfBx0uksI8VqrJ6EzfYOgz5HbcbbAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:14:37.342575Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.06042","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96a7bb75468b157906059a7142f6e12bfdf60e5c88c81ccfb29fa3b918357d53","sha256:8d71062d3ecf55e1a5877833343c113515c80ed5a182be54b2e3ca82f2fc898c"],"state_sha256":"ee617612412c7c83d39ec0fb41b352629598eca9221022bf97218e7c093626b4"}