{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:467ZRZDMVYWIEJJ6AKDHSJXLU2","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":"72ac8bbb44e49919eba11a81bafdff973c4b21aad315eb9bac4c3688e76eb2c3","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-10T07:23:27Z","title_canon_sha256":"6b14fd78e4ab8effb797d64622dd8a2afb760fb9265fb66110e05f4eb87d3e8c"},"schema_version":"1.0","source":{"id":"1907.04543","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.04543","created_at":"2026-07-05T01:53:46Z"},{"alias_kind":"arxiv_version","alias_value":"1907.04543v4","created_at":"2026-07-05T01:53:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.04543","created_at":"2026-07-05T01:53:46Z"},{"alias_kind":"pith_short_12","alias_value":"467ZRZDMVYWI","created_at":"2026-07-05T01:53:46Z"},{"alias_kind":"pith_short_16","alias_value":"467ZRZDMVYWIEJJ6","created_at":"2026-07-05T01:53:46Z"},{"alias_kind":"pith_short_8","alias_value":"467ZRZDM","created_at":"2026-07-05T01:53:46Z"}],"graph_snapshots":[{"event_id":"sha256:a687de833e4289ee39cd309ed84ed542f936a96abb09027f66b7fb46acb981a4","target":"graph","created_at":"2026-07-05T01:53:46Z","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/1907.04543/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Off-policy reinforcement learning (RL) using a fixed offline dataset of logged interactions is an important consideration in real world applications. This paper studies offline RL using the DQN replay dataset comprising the entire replay experience of a DQN agent on 60 Atari 2600 games. We demonstrate that recent off-policy deep RL algorithms, even when trained solely on this fixed dataset, outperform the fully trained DQN agent. To enhance generalization in the offline setting, we present Random Ensemble Mixture (REM), a robust Q-learning algorithm that enforces optimal Bellman consistency on","authors_text":"Dale Schuurmans, Mohammad Norouzi, Rishabh Agarwal","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-10T07:23:27Z","title":"An Optimistic Perspective on Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.04543","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":"sha256:9498376fb4c36f70fa725ecf49e0443dc674893c9981bb0e79f5a287466d79ae","target":"record","created_at":"2026-07-05T01:53:46Z","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":"72ac8bbb44e49919eba11a81bafdff973c4b21aad315eb9bac4c3688e76eb2c3","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-10T07:23:27Z","title_canon_sha256":"6b14fd78e4ab8effb797d64622dd8a2afb760fb9265fb66110e05f4eb87d3e8c"},"schema_version":"1.0","source":{"id":"1907.04543","kind":"arxiv","version":4}},"canonical_sha256":"e7bf98e46cae2c82253e02867926eba68b54acec75d6ad92881c1e6522bc9925","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7bf98e46cae2c82253e02867926eba68b54acec75d6ad92881c1e6522bc9925","first_computed_at":"2026-07-05T01:53:46.169607Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:53:46.169607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sA0gYHf15rO1vfAaS5pho+Fbwo/m8aaU71up5auIfEq37O6rX4W94Qfh6/2S3CdcKMTGtvtGhr21/wMxSJf4BA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:53:46.170026Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.04543","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9498376fb4c36f70fa725ecf49e0443dc674893c9981bb0e79f5a287466d79ae","sha256:a687de833e4289ee39cd309ed84ed542f936a96abb09027f66b7fb46acb981a4"],"state_sha256":"7c9e462caa7d9b967575c702241d14aea19fd484d927bf2da9c14cc242b7855d"}