{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:JMZWHW6ABQFI53L2BTZJOOW7CK","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":"94dee594e87cd801e4c9e8184f8121b49ab89c56bb36b156fac883e51cfe4392","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-06T17:48:17Z","title_canon_sha256":"bea25808c8e0fb21f4f468fc07394615f0ef4a39f65d4aa66d35fbc7850b64fd"},"schema_version":"1.0","source":{"id":"1908.02269","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.02269","created_at":"2026-07-05T01:50:10Z"},{"alias_kind":"arxiv_version","alias_value":"1908.02269v4","created_at":"2026-07-05T01:50:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.02269","created_at":"2026-07-05T01:50:10Z"},{"alias_kind":"pith_short_12","alias_value":"JMZWHW6ABQFI","created_at":"2026-07-05T01:50:10Z"},{"alias_kind":"pith_short_16","alias_value":"JMZWHW6ABQFI53L2","created_at":"2026-07-05T01:50:10Z"},{"alias_kind":"pith_short_8","alias_value":"JMZWHW6A","created_at":"2026-07-05T01:50:10Z"}],"graph_snapshots":[{"event_id":"sha256:54911aec5fe249c6d1c9ad8c4db10668b8a98256251924e93943dd0fc380eb63","target":"graph","created_at":"2026-07-05T01:50:10Z","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/1908.02269/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In multi-agent reinforcement learning, discovering successful collective behaviors is challenging as it requires exploring a joint action space that grows exponentially with the number of agents. While the tractability of independent agent-wise exploration is appealing, this approach fails on tasks that require elaborate group strategies. We argue that coordinating the agents' policies can guide their exploration and we investigate techniques to promote such an inductive bias. We propose two policy regularization methods: TeamReg, which is based on inter-agent action predictability and CoachRe","authors_text":"Christopher Pal, Derek Nowrouzezahrai, F\\'elix G. Harvey, Julien Roy, Paul Barde","cross_cats":["cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-06T17:48:17Z","title":"Promoting Coordination through Policy Regularization in Multi-Agent Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.02269","kind":"arxiv","version":4},"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:d823dfa251ae77ee57d2c2901b18377ca412d182dd23860f499aaf31d642caee","target":"record","created_at":"2026-07-05T01:50:10Z","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":"94dee594e87cd801e4c9e8184f8121b49ab89c56bb36b156fac883e51cfe4392","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-06T17:48:17Z","title_canon_sha256":"bea25808c8e0fb21f4f468fc07394615f0ef4a39f65d4aa66d35fbc7850b64fd"},"schema_version":"1.0","source":{"id":"1908.02269","kind":"arxiv","version":4}},"canonical_sha256":"4b3363dbc00c0a8eed7a0cf2973adf12b1893d5c13790e2cb530629d1a764535","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b3363dbc00c0a8eed7a0cf2973adf12b1893d5c13790e2cb530629d1a764535","first_computed_at":"2026-07-05T01:50:10.952300Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:50:10.952300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"igNi/ePsAbAHtJxm7MsSAGbJFXBm2yT4P/UEUy4lnz1hRBYFQzpfnplPeO7wu0+Zuo7xvLbklLv7o/AavHdhDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:50:10.952756Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.02269","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d823dfa251ae77ee57d2c2901b18377ca412d182dd23860f499aaf31d642caee","sha256:54911aec5fe249c6d1c9ad8c4db10668b8a98256251924e93943dd0fc380eb63"],"state_sha256":"ee6702022b5b9d81e94befcbdfc9a223d2551e435fa8f4538498800fcd5d45d3"}