{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TTCAXWKNNHEEERLWX32TQW4MZN","short_pith_number":"pith:TTCAXWKN","schema_version":"1.0","canonical_sha256":"9cc40bd94d69c8424576bef5385b8ccb5ae43f3e8fcd2a64912a0a6985a1e466","source":{"kind":"arxiv","id":"1910.01708","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Batch Deep Reinforcement Learning Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Many batch deep RL algorithms underperform online DQN and the behavioral policy itself when trained on fixed Atari data from one policy.","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Edoardo Conti, Joelle Pineau, Mohammad Ghavamzadeh, Scott Fujimoto","submitted_at":"2019-10-03T20:15:55Z","abstract_excerpt":"Widely-used deep reinforcement learning algorithms have been shown to fail in the batch setting--learning from a fixed data set without interaction with the environment. Following this result, there have been several papers showing reasonable performances under a variety of environments and batch settings. In this paper, we benchmark the performance of recent off-policy and batch reinforcement learning algorithms under unified settings on the Atari domain, with data generated by a single partially-trained behavioral policy. We find that under these conditions, many of these algorithms underper"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"1910.01708","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-03T20:15:55Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"b288aedd284dd5187b25b9614e70486df3cd2fa1a6c57e096f443186d963459a","abstract_canon_sha256":"52bc3739e1831baf67e8a14a5a40e7555d91c254c91c18d67b8f2c5ea670ac68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:13.297517Z","signature_b64":"lEePs2yBoSR9FJ4qqy3S5AfOM9B9VOmvZOvZdgkyAvaPmc15Mh3nZEGBo5mg0omrXlMTHJHhuTIO1U3XBblPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cc40bd94d69c8424576bef5385b8ccb5ae43f3e8fcd2a64912a0a6985a1e466","last_reissued_at":"2026-05-17T23:38:13.296922Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:13.296922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Batch Deep Reinforcement Learning Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Many batch deep RL algorithms underperform online DQN and the behavioral policy itself when trained on fixed Atari data from one policy.","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Edoardo Conti, Joelle Pineau, Mohammad Ghavamzadeh, Scott Fujimoto","submitted_at":"2019-10-03T20:15:55Z","abstract_excerpt":"Widely-used deep reinforcement learning algorithms have been shown to fail in the batch setting--learning from a fixed data set without interaction with the environment. Following this result, there have been several papers showing reasonable performances under a variety of environments and batch settings. In this paper, we benchmark the performance of recent off-policy and batch reinforcement learning algorithms under unified settings on the Atari domain, with data generated by a single partially-trained behavioral policy. We find that under these conditions, many of these algorithms underper"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"under these conditions, many of these algorithms underperform DQN trained online with the same amount of data, as well as the partially-trained behavioral policy. ... we adapt the Batch-Constrained Q-learning algorithm to a discrete-action setting, and show it outperforms all existing algorithms at this task.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That data generated by a single partially-trained behavioral policy under unified settings produces a representative and fair testbed for comparing batch RL algorithms.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Many batch RL algorithms underperform both online DQN and the behavioral policy on Atari; an adapted discrete-action BCQ outperforms the others tested.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Many batch deep RL algorithms underperform online DQN and the behavioral policy itself when trained on fixed Atari data from one policy.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a166490578a6cf086f90d485b3ccaede0b58f6148046db76d51db23d88f1f8ad"},"source":{"id":"1910.01708","kind":"arxiv","version":1},"verdict":{"id":"b0a6fd49-69b5-4df4-b81d-9d426bf70cc4","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T19:24:29.450533Z","strongest_claim":"under these conditions, many of these algorithms underperform DQN trained online with the same amount of data, as well as the partially-trained behavioral policy. ... we adapt the Batch-Constrained Q-learning algorithm to a discrete-action setting, and show it outperforms all existing algorithms at this task.","one_line_summary":"Many batch RL algorithms underperform both online DQN and the behavioral policy on Atari; an adapted discrete-action BCQ outperforms the others tested.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That data generated by a single partially-trained behavioral policy under unified settings produces a representative and fair testbed for comparing batch RL algorithms.","pith_extraction_headline":"Many batch deep RL algorithms underperform online DQN and the behavioral policy itself when trained on fixed Atari data from one policy."},"references":{"count":18,"sample":[{"doi":"","year":1907,"title":"Striving for simplicity in off-policy deep reinforcement learning.arXiv preprint arXiv:1907.04543","work_id":"588a4dc4-2821-4960-ab47-4a85390287c3","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Exploration by random network distillation","work_id":"5a87fef6-96e2-4d5b-91ec-1a7c9a43cab9","ref_index":2,"cited_arxiv_id":"1810.12894","is_internal_anchor":true},{"doi":"","year":null,"title":"Dopamine: A research framework for deep reinforcement learning","work_id":"a0c1e29f-e775-49dc-977e-bbbca0daa6d8","ref_index":3,"cited_arxiv_id":"1812.06110","is_internal_anchor":true},{"doi":"","year":null,"title":"Bellemare, and R´ emi Munos","work_id":"f3531420-1352-4be7-b9b7-229fb79f889d","ref_index":4,"cited_arxiv_id":"1710.10044","is_internal_anchor":true},{"doi":"","year":2052,"title":"Off-policy deep reinforcement learning without exploration","work_id":"9bd09ac4-5e91-4d50-9e9b-38436443b511","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":18,"snapshot_sha256":"cf15819122f07fb9170bf0b70ce830d22d3a93022edc2c398111ffc6da057e4c","internal_anchors":7},"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":"1910.01708","created_at":"2026-05-17T23:38:13.297030+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.01708v1","created_at":"2026-05-17T23:38:13.297030+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.01708","created_at":"2026-05-17T23:38:13.297030+00:00"},{"alias_kind":"pith_short_12","alias_value":"TTCAXWKNNHEE","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"TTCAXWKNNHEEERLW","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"TTCAXWKN","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":17,"sample":[{"citing_arxiv_id":"2510.11491","citing_title":"Constraint-Aware Reinforcement Learning via Adaptive Action Scaling","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14043","citing_title":"Optimal design of solar-battery hybrid resources considering multi-market participation under weather and price uncertainty","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14174","citing_title":"Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14246","citing_title":"Action-Conditioned Risk Gating for Safety-Critical Control under Partial Observability","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2604.00904","citing_title":"Fatigue-Aware Learning to Defer via Constrained Optimisation","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03489","citing_title":"Improving Feasibility via Fast Autoencoder-Based Projections","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11688","citing_title":"Shaping Zero-Shot Coordination via State Blocking","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11975","citing_title":"Stochastic Minimum-Cost Reach-Avoid Reinforcement Learning","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11694","citing_title":"Augmented Lagrangian Method for Last-Iterate Convergence for Constrained MDPs","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23576","citing_title":"CAPSULE: Control-Theoretic Action Perturbations for Safe Uncertainty-Aware Reinforcement Learning","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05172","citing_title":"When Life Gives You BC, Make Q-functions: Extracting Q-values from Behavior Cloning for On-Robot Reinforcement Learning","ref_index":69,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00667","citing_title":"Augmented Lagrangian Multiplier Network for State-wise Safety in Reinforcement Learning","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2604.12667","citing_title":"Safe reinforcement learning with online filtering for fatigue-predictive human-robot task planning and allocation in production","ref_index":67,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07457","citing_title":"CMP: Robust Whole-Body Tracking for Loco-Manipulation via Competence Manifold Projection","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06730","citing_title":"Semantic State Abstraction Interfaces for LLM-Augmented Portfolio Decisions: Multi-Axis News Decomposition and RL Diagnostics","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06934","citing_title":"Learned Lyapunov Shielding for Adaptive Control","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06992","citing_title":"Why Does Agentic Safety Fail to Generalize Across Tasks?","ref_index":93,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TTCAXWKNNHEEERLWX32TQW4MZN","json":"https://pith.science/pith/TTCAXWKNNHEEERLWX32TQW4MZN.json","graph_json":"https://pith.science/api/pith-number/TTCAXWKNNHEEERLWX32TQW4MZN/graph.json","events_json":"https://pith.science/api/pith-number/TTCAXWKNNHEEERLWX32TQW4MZN/events.json","paper":"https://pith.science/paper/TTCAXWKN"},"agent_actions":{"view_html":"https://pith.science/pith/TTCAXWKNNHEEERLWX32TQW4MZN","download_json":"https://pith.science/pith/TTCAXWKNNHEEERLWX32TQW4MZN.json","view_paper":"https://pith.science/paper/TTCAXWKN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.01708&json=true","fetch_graph":"https://pith.science/api/pith-number/TTCAXWKNNHEEERLWX32TQW4MZN/graph.json","fetch_events":"https://pith.science/api/pith-number/TTCAXWKNNHEEERLWX32TQW4MZN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TTCAXWKNNHEEERLWX32TQW4MZN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TTCAXWKNNHEEERLWX32TQW4MZN/action/storage_attestation","attest_author":"https://pith.science/pith/TTCAXWKNNHEEERLWX32TQW4MZN/action/author_attestation","sign_citation":"https://pith.science/pith/TTCAXWKNNHEEERLWX32TQW4MZN/action/citation_signature","submit_replication":"https://pith.science/pith/TTCAXWKNNHEEERLWX32TQW4MZN/action/replication_record"}},"created_at":"2026-05-17T23:38:13.297030+00:00","updated_at":"2026-05-17T23:38:13.297030+00:00"}