{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BIZLOEVHM5NNFXOOG22BIKT2TZ","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":"3482b8ec1a53f6b9df47414d9e434e26016c4b2b00f32c0694d042bd34d6744f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-30T16:31:04Z","title_canon_sha256":"c11aa7d7db89c3c446c412d3eaadfc14c837ce67695d8bf69d4891cde47589e2"},"schema_version":"1.0","source":{"id":"2311.18684","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.18684","created_at":"2026-07-05T07:18:45Z"},{"alias_kind":"arxiv_version","alias_value":"2311.18684v1","created_at":"2026-07-05T07:18:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.18684","created_at":"2026-07-05T07:18:45Z"},{"alias_kind":"pith_short_12","alias_value":"BIZLOEVHM5NN","created_at":"2026-07-05T07:18:45Z"},{"alias_kind":"pith_short_16","alias_value":"BIZLOEVHM5NNFXOO","created_at":"2026-07-05T07:18:45Z"},{"alias_kind":"pith_short_8","alias_value":"BIZLOEVH","created_at":"2026-07-05T07:18:45Z"}],"graph_snapshots":[{"event_id":"sha256:0bfe404ae48475c057e9fc9907c405ba9aa80e20c855ad8b6aeaad309e02e05a","target":"graph","created_at":"2026-07-05T07:18:45Z","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/2311.18684/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"By reusing data throughout training, off-policy deep reinforcement learning algorithms offer improved sample efficiency relative to on-policy approaches. For continuous action spaces, the most popular methods for off-policy learning include policy improvement steps where a learned state-action ($Q$) value function is maximized over selected batches of data. These updates are often paired with regularization to combat associated overestimation of $Q$ values. With an eye toward safety, we revisit this strategy in environments with \"mixed-sign\" reward functions; that is, with reward functions tha","authors_text":"Gary Collins, Jared Markowitz, Jesse Silverberg","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-30T16:31:04Z","title":"Handling Cost and Constraints with Off-Policy Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.18684","kind":"arxiv","version":1},"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":"sha256:4c1b6b73015f10189f553fd13ff603708910ff5ead6b10c91554cac92ca4842e","target":"record","created_at":"2026-07-05T07:18:45Z","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":"3482b8ec1a53f6b9df47414d9e434e26016c4b2b00f32c0694d042bd34d6744f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-30T16:31:04Z","title_canon_sha256":"c11aa7d7db89c3c446c412d3eaadfc14c837ce67695d8bf69d4891cde47589e2"},"schema_version":"1.0","source":{"id":"2311.18684","kind":"arxiv","version":1}},"canonical_sha256":"0a32b712a7675ad2ddce36b4142a7a9e4031ba594ec10684263f8a7d7ee50c70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a32b712a7675ad2ddce36b4142a7a9e4031ba594ec10684263f8a7d7ee50c70","first_computed_at":"2026-07-05T07:18:45.290195Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:18:45.290195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CeQy7lEUjRUC29i4A/7+T7nVWxm67TLujqqC4JomyxLvLfIgAIaXvOhbIcThmEIqLeV9kX+HL1t+E0+6cEIwDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:18:45.290575Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.18684","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c1b6b73015f10189f553fd13ff603708910ff5ead6b10c91554cac92ca4842e","sha256:0bfe404ae48475c057e9fc9907c405ba9aa80e20c855ad8b6aeaad309e02e05a"],"state_sha256":"61c7184915df7e6e987b0f464457038bb37da3c5f9b3fc08558f4f99f52f8142"}