{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:KPKJM53ZLN2ZX5POXXZELNJBFH","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":"34eff04d7980b40635399a4fc51672c4a5bd3c01741a950000a18741fd756fb9","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-27T04:43:19Z","title_canon_sha256":"c3f5397707266d429781d6ffa88f5c365205cc140ce54eb116d1695d5e92d932"},"schema_version":"1.0","source":{"id":"1910.12179","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.12179","created_at":"2026-07-05T01:48:06Z"},{"alias_kind":"arxiv_version","alias_value":"1910.12179v4","created_at":"2026-07-05T01:48:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.12179","created_at":"2026-07-05T01:48:06Z"},{"alias_kind":"pith_short_12","alias_value":"KPKJM53ZLN2Z","created_at":"2026-07-05T01:48:06Z"},{"alias_kind":"pith_short_16","alias_value":"KPKJM53ZLN2ZX5PO","created_at":"2026-07-05T01:48:06Z"},{"alias_kind":"pith_short_8","alias_value":"KPKJM53Z","created_at":"2026-07-05T01:48:06Z"}],"graph_snapshots":[{"event_id":"sha256:07bfaf82b39a9a22da330fbad870509a60efc14871567bb9703d051c091812b5","target":"graph","created_at":"2026-07-05T01:48:06Z","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/1910.12179/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There has recently been a surge in research in batch Deep Reinforcement Learning (DRL), which aims for learning a high-performing policy from a given dataset without additional interactions with the environment. We propose a new algorithm, Best-Action Imitation Learning (BAIL), which strives for both simplicity and performance. BAIL learns a V function, uses the V function to select actions it believes to be high-performing, and then uses those actions to train a policy network using imitation learning. For the MuJoCo benchmark, we provide a comprehensive experimental study of BAIL, comparing ","authors_text":"Che Wang, Keith Ross, Xinyue Chen, Yanqiu Wu, Zheng Wang, Zijian Zhou","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-27T04:43:19Z","title":"BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.12179","kind":"arxiv","version":4},"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":"sha256:5540c1823bcc58f251a86955e0716be1e3fbb29b6621bef46616bdfbac8c5b4d","target":"record","created_at":"2026-07-05T01:48:06Z","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":"34eff04d7980b40635399a4fc51672c4a5bd3c01741a950000a18741fd756fb9","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-27T04:43:19Z","title_canon_sha256":"c3f5397707266d429781d6ffa88f5c365205cc140ce54eb116d1695d5e92d932"},"schema_version":"1.0","source":{"id":"1910.12179","kind":"arxiv","version":4}},"canonical_sha256":"53d49677795b759bf5eebdf245b52129ecad55367536b94bcb58e7c26e517716","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53d49677795b759bf5eebdf245b52129ecad55367536b94bcb58e7c26e517716","first_computed_at":"2026-07-05T01:48:06.907154Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:48:06.907154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T3OHQg3Mwd5JzBo1LLitQu82kssrLjw+1iBCsgJATCGAey2qw2d7ouXJV4XLthaTlNyBytV/C5i9X1UoYqBNBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:48:06.907591Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.12179","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5540c1823bcc58f251a86955e0716be1e3fbb29b6621bef46616bdfbac8c5b4d","sha256:07bfaf82b39a9a22da330fbad870509a60efc14871567bb9703d051c091812b5"],"state_sha256":"71f18f5bc12ecd45dd2bccfdb8c4532f67e8df930bd73a48dd907db713a90ac2"}