{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HLQLOD42RW56EHVJBBQIMQG4GO","short_pith_number":"pith:HLQLOD42","schema_version":"1.0","canonical_sha256":"3ae0b70f9a8dbbe21ea908608640dc3384f40c2aaebf3480cfd07148e39de11a","source":{"kind":"arxiv","id":"2006.10410","version":2},"attestation_state":"computed","paper":{"title":"DREAM: Deep Regret minimization with Advantage baselines and Model-free learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Lerer, Eric Steinberger, Noam Brown","submitted_at":"2020-06-18T10:30:27Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2006.10410","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T10:30:27Z","cross_cats_sorted":["cs.GT","stat.ML"],"title_canon_sha256":"8e8c07e86a0900b379c4d51ceac5d053eb14987045198cb7dde8e3ba4dee0eb2","abstract_canon_sha256":"edcdd2aa164328a6d21260089eb1b8878ecc31227ff72af85d5ea460748f0015"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:55:10.746851Z","signature_b64":"7v0lOFfehOr5PQp3+44XqaUA2kEBJCyY4W2252gi1Xgcsv/JW4/20U70QoeGzYt4yUl8yVrAA1D6NJ0A/wXiBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ae0b70f9a8dbbe21ea908608640dc3384f40c2aaebf3480cfd07148e39de11a","last_reissued_at":"2026-07-05T01:55:10.746402Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:55:10.746402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DREAM: Deep Regret minimization with Advantage baselines and Model-free learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Lerer, Eric Steinberger, Noam Brown","submitted_at":"2020-06-18T10:30:27Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.10410","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.10410/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2006.10410","created_at":"2026-07-05T01:55:10.746461+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.10410v2","created_at":"2026-07-05T01:55:10.746461+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.10410","created_at":"2026-07-05T01:55:10.746461+00:00"},{"alias_kind":"pith_short_12","alias_value":"HLQLOD42RW56","created_at":"2026-07-05T01:55:10.746461+00:00"},{"alias_kind":"pith_short_16","alias_value":"HLQLOD42RW56EHVJ","created_at":"2026-07-05T01:55:10.746461+00:00"},{"alias_kind":"pith_short_8","alias_value":"HLQLOD42","created_at":"2026-07-05T01:55:10.746461+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11284","citing_title":"Phi-Actor-Critic: Steering General-Sum Games to Pareto-Efficient Correlated Equilibria","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2510.18183","citing_title":"NashPG: A Policy Gradient Method with Iteratively Refined Regularization for Finding Nash Equilibria","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14379","citing_title":"Data-Augmented Game Starts for Accelerating Self-Play Exploration in Imperfect Information Games","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09150","citing_title":"AlphaExploitem: Going Beyond the Nash Equilibrium in Poker by Learning to Exploit Suboptimal Play","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HLQLOD42RW56EHVJBBQIMQG4GO","json":"https://pith.science/pith/HLQLOD42RW56EHVJBBQIMQG4GO.json","graph_json":"https://pith.science/api/pith-number/HLQLOD42RW56EHVJBBQIMQG4GO/graph.json","events_json":"https://pith.science/api/pith-number/HLQLOD42RW56EHVJBBQIMQG4GO/events.json","paper":"https://pith.science/paper/HLQLOD42"},"agent_actions":{"view_html":"https://pith.science/pith/HLQLOD42RW56EHVJBBQIMQG4GO","download_json":"https://pith.science/pith/HLQLOD42RW56EHVJBBQIMQG4GO.json","view_paper":"https://pith.science/paper/HLQLOD42","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.10410&json=true","fetch_graph":"https://pith.science/api/pith-number/HLQLOD42RW56EHVJBBQIMQG4GO/graph.json","fetch_events":"https://pith.science/api/pith-number/HLQLOD42RW56EHVJBBQIMQG4GO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HLQLOD42RW56EHVJBBQIMQG4GO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HLQLOD42RW56EHVJBBQIMQG4GO/action/storage_attestation","attest_author":"https://pith.science/pith/HLQLOD42RW56EHVJBBQIMQG4GO/action/author_attestation","sign_citation":"https://pith.science/pith/HLQLOD42RW56EHVJBBQIMQG4GO/action/citation_signature","submit_replication":"https://pith.science/pith/HLQLOD42RW56EHVJBBQIMQG4GO/action/replication_record"}},"created_at":"2026-07-05T01:55:10.746461+00:00","updated_at":"2026-07-05T01:55:10.746461+00:00"}