{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:HLQLOD42RW56EHVJBBQIMQG4GO","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":"edcdd2aa164328a6d21260089eb1b8878ecc31227ff72af85d5ea460748f0015","cross_cats_sorted":["cs.GT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T10:30:27Z","title_canon_sha256":"8e8c07e86a0900b379c4d51ceac5d053eb14987045198cb7dde8e3ba4dee0eb2"},"schema_version":"1.0","source":{"id":"2006.10410","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.10410","created_at":"2026-07-05T01:55:10Z"},{"alias_kind":"arxiv_version","alias_value":"2006.10410v2","created_at":"2026-07-05T01:55:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.10410","created_at":"2026-07-05T01:55:10Z"},{"alias_kind":"pith_short_12","alias_value":"HLQLOD42RW56","created_at":"2026-07-05T01:55:10Z"},{"alias_kind":"pith_short_16","alias_value":"HLQLOD42RW56EHVJ","created_at":"2026-07-05T01:55:10Z"},{"alias_kind":"pith_short_8","alias_value":"HLQLOD42","created_at":"2026-07-05T01:55:10Z"}],"graph_snapshots":[{"event_id":"sha256:71558f6ab61ac52a254645757374e9128115e74e9b0b852a85cf91063ae3e56a","target":"graph","created_at":"2026-07-05T01:55:10Z","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/2006.10410/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce DREAM, a deep reinforcement learning algorithm that finds optimal strategies in imperfect-information games with multiple agents. Formally, DREAM converges to a Nash Equilibrium in two-player zero-sum games and to an extensive-form coarse correlated equilibrium in all other games. Our primary innovation is an effective algorithm that, in contrast to other regret-based deep learning algorithms, does not require access to a perfect simulator of the game to achieve good performance. We show that DREAM empirically achieves state-of-the-art performance among model-free algorithms in po","authors_text":"Adam Lerer, Eric Steinberger, Noam Brown","cross_cats":["cs.GT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T10:30:27Z","title":"DREAM: Deep Regret minimization with Advantage baselines and Model-free learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.10410","kind":"arxiv","version":2},"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":"sha256:1cc3a4b5d4c39e4cdd7eec1511fc4e0c22cc78b1f8f4dd84a749fc1a7cf59d8f","target":"record","created_at":"2026-07-05T01:55:10Z","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":"edcdd2aa164328a6d21260089eb1b8878ecc31227ff72af85d5ea460748f0015","cross_cats_sorted":["cs.GT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T10:30:27Z","title_canon_sha256":"8e8c07e86a0900b379c4d51ceac5d053eb14987045198cb7dde8e3ba4dee0eb2"},"schema_version":"1.0","source":{"id":"2006.10410","kind":"arxiv","version":2}},"canonical_sha256":"3ae0b70f9a8dbbe21ea908608640dc3384f40c2aaebf3480cfd07148e39de11a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ae0b70f9a8dbbe21ea908608640dc3384f40c2aaebf3480cfd07148e39de11a","first_computed_at":"2026-07-05T01:55:10.746402Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:55:10.746402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7v0lOFfehOr5PQp3+44XqaUA2kEBJCyY4W2252gi1Xgcsv/JW4/20U70QoeGzYt4yUl8yVrAA1D6NJ0A/wXiBg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:55:10.746851Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.10410","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1cc3a4b5d4c39e4cdd7eec1511fc4e0c22cc78b1f8f4dd84a749fc1a7cf59d8f","sha256:71558f6ab61ac52a254645757374e9128115e74e9b0b852a85cf91063ae3e56a"],"state_sha256":"4f34ebbd6ed263e696c0c3ff0e4bc90d50523bb2483d2e3792b8a194cc138c73"}