{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:IPVEHNFDKGIITZTV72HWCKOPT7","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":"3133818af109e1d37fee6f9f5175f48282c82883fb8ed917fee124a996152dcd","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-07T02:59:59Z","title_canon_sha256":"0c46dba128aca11da70ce113a2d9af875d04cd7d9a2558d7cb76d3e9dd9fb8ab"},"schema_version":"1.0","source":{"id":"2001.01866","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.01866","created_at":"2026-07-05T00:32:40Z"},{"alias_kind":"arxiv_version","alias_value":"2001.01866v2","created_at":"2026-07-05T00:32:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.01866","created_at":"2026-07-05T00:32:40Z"},{"alias_kind":"pith_short_12","alias_value":"IPVEHNFDKGII","created_at":"2026-07-05T00:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"IPVEHNFDKGIITZTV","created_at":"2026-07-05T00:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"IPVEHNFD","created_at":"2026-07-05T00:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:bc66c4d3581f75d205eaba59b9bc0fa3d4f82c90dd4778b70b0d001d9e299270","target":"graph","created_at":"2026-07-05T00:32:40Z","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/2001.01866/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We review basic concepts of convex duality, focusing on the very general and supremely useful Fenchel-Rockafellar duality. We summarize how this duality may be applied to a variety of reinforcement learning (RL) settings, including policy evaluation or optimization, online or offline learning, and discounted or undiscounted rewards. The derivations yield a number of intriguing results, including the ability to perform policy evaluation and on-policy policy gradient with behavior-agnostic offline data and methods to learn a policy via max-likelihood optimization. Although many of these results ","authors_text":"Bo Dai, Ofir Nachum","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-07T02:59:59Z","title":"Reinforcement Learning via Fenchel-Rockafellar Duality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.01866","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":"sha256:2530a5043026adcb4efebff5c608d3ec9450914ae90519c3e0b4515179bee0d7","target":"record","created_at":"2026-07-05T00:32:40Z","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":"3133818af109e1d37fee6f9f5175f48282c82883fb8ed917fee124a996152dcd","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-07T02:59:59Z","title_canon_sha256":"0c46dba128aca11da70ce113a2d9af875d04cd7d9a2558d7cb76d3e9dd9fb8ab"},"schema_version":"1.0","source":{"id":"2001.01866","kind":"arxiv","version":2}},"canonical_sha256":"43ea43b4a3519089e675fe8f6129cf9fe4b8362f25128b23af17ccc983e83279","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43ea43b4a3519089e675fe8f6129cf9fe4b8362f25128b23af17ccc983e83279","first_computed_at":"2026-07-05T00:32:40.799710Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:32:40.799710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ubwOKuEcZD7EIANlHOiecGpIgankshG+Dz5dbinnhdRzLWHAB89u/D6MPcCsfm7TFykAjBLixH/1fpddTkIjAA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:32:40.800135Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.01866","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2530a5043026adcb4efebff5c608d3ec9450914ae90519c3e0b4515179bee0d7","sha256:bc66c4d3581f75d205eaba59b9bc0fa3d4f82c90dd4778b70b0d001d9e299270"],"state_sha256":"b05eefba39bd5de207a556adc82b73a207c4231324fefde9f229f79ae01b6d55"}