{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:RWXMS4M6VQQLPTAH5UVU5MNJ2E","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":"9ac60f047e13e6401c90e67ebf2d8c1078ba6228b8ac109b08a30a20e35f275e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2020-11-23T16:28:27Z","title_canon_sha256":"e272c276fad178524f8537a46054c67b3f17e0a93eb964b96183b0187bb64640"},"schema_version":"1.0","source":{"id":"2011.11517","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.11517","created_at":"2026-07-05T11:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"2011.11517v1","created_at":"2026-07-05T11:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.11517","created_at":"2026-07-05T11:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"RWXMS4M6VQQL","created_at":"2026-07-05T11:03:44Z"},{"alias_kind":"pith_short_16","alias_value":"RWXMS4M6VQQLPTAH","created_at":"2026-07-05T11:03:44Z"},{"alias_kind":"pith_short_8","alias_value":"RWXMS4M6","created_at":"2026-07-05T11:03:44Z"}],"graph_snapshots":[{"event_id":"sha256:7a6bb9b6eb55403edd9154a7f04d46d9caf7544cbe44307c0a3ce762cfab7c1c","target":"graph","created_at":"2026-07-05T11:03:44Z","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/2011.11517/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces an information-theoretic constraint on learned policy complexity in the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) reinforcement learning algorithm. Previous research with a related approach in continuous control experiments suggests that this method favors learning policies that are more robust to changing environment dynamics. The multi-agent game setting naturally requires this type of robustness, as other agents' policies change throughout learning, introducing a nonstationary environment. For this reason, recent methods in continual learning are compared","authors_text":"Chris R. Sims, Gerald Tesauro, Matthew Riemer, Miao Liu, Tailia Malloy, Tim Klinger","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2020-11-23T16:28:27Z","title":"Consolidation via Policy Information Regularization in Deep RL for Multi-Agent Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.11517","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":"sha256:97ebb16e22a4604d5397637c971902de5a3fc2c421ae0dfdfa38beacf16425ff","target":"record","created_at":"2026-07-05T11:03:44Z","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":"9ac60f047e13e6401c90e67ebf2d8c1078ba6228b8ac109b08a30a20e35f275e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2020-11-23T16:28:27Z","title_canon_sha256":"e272c276fad178524f8537a46054c67b3f17e0a93eb964b96183b0187bb64640"},"schema_version":"1.0","source":{"id":"2011.11517","kind":"arxiv","version":1}},"canonical_sha256":"8daec9719eac20b7cc07ed2b4eb1a9d113bdbe336f6ab85d0a0497cc50d33498","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8daec9719eac20b7cc07ed2b4eb1a9d113bdbe336f6ab85d0a0497cc50d33498","first_computed_at":"2026-07-05T11:03:44.274923Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:44.274923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2NYAnxdiUIzRDbA+1B25zOfSFvJN3fcGJ1Ceiu0tHuINGShJ4whEmnbng0HTOKA1JUSgHzmde9hPIKRrTjjoAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:44.275437Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.11517","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97ebb16e22a4604d5397637c971902de5a3fc2c421ae0dfdfa38beacf16425ff","sha256:7a6bb9b6eb55403edd9154a7f04d46d9caf7544cbe44307c0a3ce762cfab7c1c"],"state_sha256":"8b477ddf949764b5765370a5d0ae7f9f1963e0840ab6af0ab83a81b458d92296"}