{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:EMCXRTXZI35VOWDLKDYYLFDI7D","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":"9b78aaa841635242a8319b84ba9742443118793cef31f8ad7accc10b9bbb9b50","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-08-27T16:30:17Z","title_canon_sha256":"b787660052535a0debd148f4ad3d984ff47280bbf1fb4ba65a9009f03d1c9601"},"schema_version":"1.0","source":{"id":"2008.12234","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.12234","created_at":"2026-07-05T01:31:04Z"},{"alias_kind":"arxiv_version","alias_value":"2008.12234v1","created_at":"2026-07-05T01:31:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.12234","created_at":"2026-07-05T01:31:04Z"},{"alias_kind":"pith_short_12","alias_value":"EMCXRTXZI35V","created_at":"2026-07-05T01:31:04Z"},{"alias_kind":"pith_short_16","alias_value":"EMCXRTXZI35VOWDL","created_at":"2026-07-05T01:31:04Z"},{"alias_kind":"pith_short_8","alias_value":"EMCXRTXZ","created_at":"2026-07-05T01:31:04Z"}],"graph_snapshots":[{"event_id":"sha256:46b9c522d0877a263a253c14dec34547288869c56d88922b560c64985da55e72","target":"graph","created_at":"2026-07-05T01:31:04Z","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/2008.12234/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Regret minimization has played a key role in online learning, equilibrium computation in games, and reinforcement learning (RL). In this paper, we describe a general model-free RL method for no-regret learning based on repeated reconsideration of past behavior. We propose a model-free RL algorithm, the AdvantageRegret-Matching Actor-Critic (ARMAC): rather than saving past state-action data, ARMAC saves a buffer of past policies, replaying through them to reconstruct hindsight assessments of past behavior. These retrospective value estimates are used to predict conditional advantages which, com","authors_text":"Audr\\=unas Gruslys, Dustin Morrill, Finbarr Timbers, Jean-Baptiste Lespiau, John Schultz, Julien Perolat, Karl Tuyls, Marc Lanctot, Martin Schmid, Michael Bowling, Mohammad Gheshlaghi Azar, R\\'emi Munos, Vinicius Zambaldi","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-08-27T16:30:17Z","title":"The Advantage Regret-Matching Actor-Critic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.12234","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":"sha256:3613fbfa8ff642953cb1a4a54d8bbcda5d4d8042a37a6280b301c7275b1fc942","target":"record","created_at":"2026-07-05T01:31:04Z","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":"9b78aaa841635242a8319b84ba9742443118793cef31f8ad7accc10b9bbb9b50","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-08-27T16:30:17Z","title_canon_sha256":"b787660052535a0debd148f4ad3d984ff47280bbf1fb4ba65a9009f03d1c9601"},"schema_version":"1.0","source":{"id":"2008.12234","kind":"arxiv","version":1}},"canonical_sha256":"230578cef946fb57586b50f1859468f8c7023c18f60083786e7d77dd8584f4be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"230578cef946fb57586b50f1859468f8c7023c18f60083786e7d77dd8584f4be","first_computed_at":"2026-07-05T01:31:04.107724Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:31:04.107724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R1rJcxLkQmtddXGqmVleKmI0TT93e/WLBMac4CovtvrsKu3UlO3CAKej9Y7pksWM1M0Q73jf5mpkt8ygbngAAA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:31:04.108200Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.12234","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3613fbfa8ff642953cb1a4a54d8bbcda5d4d8042a37a6280b301c7275b1fc942","sha256:46b9c522d0877a263a253c14dec34547288869c56d88922b560c64985da55e72"],"state_sha256":"308385bcd1c3c6d5d7b4f3593d6cca5fd5eebffb973fb006dff091018e71cab9"}