{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:M2NIBJ2TBEAD7TJVU3ZDL4LSGG","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":"1ce5fbaf044bb3f3726dc06921cba2b05aeb4c2a814feb8612788564ca0858e9","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-02-19T20:22:04Z","title_canon_sha256":"b80fb8301b69cb70dae0d08e19d8cfd95dc543fedde3e987690b3e1e9a44809d"},"schema_version":"1.0","source":{"id":"2202.09673","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.09673","created_at":"2026-07-05T05:04:27Z"},{"alias_kind":"arxiv_version","alias_value":"2202.09673v2","created_at":"2026-07-05T05:04:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.09673","created_at":"2026-07-05T05:04:27Z"},{"alias_kind":"pith_short_12","alias_value":"M2NIBJ2TBEAD","created_at":"2026-07-05T05:04:27Z"},{"alias_kind":"pith_short_16","alias_value":"M2NIBJ2TBEAD7TJV","created_at":"2026-07-05T05:04:27Z"},{"alias_kind":"pith_short_8","alias_value":"M2NIBJ2T","created_at":"2026-07-05T05:04:27Z"}],"graph_snapshots":[{"event_id":"sha256:50e8b579ca2a7573ba465d7d663af3b8e1a602e49bae94a8c5eb83b948e6d9d3","target":"graph","created_at":"2026-07-05T05:04:27Z","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/2202.09673/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning enables learning from a fixed dataset, without further interactions with the environment. The lack of environmental interactions makes the policy training vulnerable to state-action pairs far from the training dataset and prone to missing rewarding actions. For training more effective agents, we propose a framework that supports learning a flexible yet well-regularized fully-implicit policy. We further propose a simple modification to the classical policy-matching methods for regularizing with respect to the dual form of the Jensen--Shannon divergence and the int","authors_text":"Huangjie Zheng, Mingyuan Zhou, Shentao Yang, Yihao Feng, Zhendong Wang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-02-19T20:22:04Z","title":"A Behavior Regularized Implicit Policy for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.09673","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":"sha256:803cffea9b1bb7898a5e7f4617fcbc6094d959ff2aa76d0d5ba9167eb0afeb46","target":"record","created_at":"2026-07-05T05:04:27Z","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":"1ce5fbaf044bb3f3726dc06921cba2b05aeb4c2a814feb8612788564ca0858e9","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-02-19T20:22:04Z","title_canon_sha256":"b80fb8301b69cb70dae0d08e19d8cfd95dc543fedde3e987690b3e1e9a44809d"},"schema_version":"1.0","source":{"id":"2202.09673","kind":"arxiv","version":2}},"canonical_sha256":"669a80a75309003fcd35a6f235f17231943006b3f9411d4e927956b55b25a941","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"669a80a75309003fcd35a6f235f17231943006b3f9411d4e927956b55b25a941","first_computed_at":"2026-07-05T05:04:27.802580Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:04:27.802580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CtZ8yjFiYmza21s1SHKR+jSJ02F/+9kxIzdV+WpriB2ZEYvz/3Tfdj7Dj+MnHlhbU1mqq+X/B7klXfYV+9RDBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:04:27.802999Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.09673","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:803cffea9b1bb7898a5e7f4617fcbc6094d959ff2aa76d0d5ba9167eb0afeb46","sha256:50e8b579ca2a7573ba465d7d663af3b8e1a602e49bae94a8c5eb83b948e6d9d3"],"state_sha256":"e10f8e5e176f410a5be3b27a0982515bc8ac74808cca2296f9c995ae66141a0c"}