{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:AVH7NMFACIN5AWTO3EG5557LR7","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":"e37bcc78139103d45a27227719d963960adef634ac7045d03e21429266ca7029","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-04T16:06:10Z","title_canon_sha256":"9ec97c19b6346ff6625df39d258d4accc4c656f288ae4467c9ffa66b3e8cf2b5"},"schema_version":"1.0","source":{"id":"1912.02074","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.02074","created_at":"2026-07-05T00:23:56Z"},{"alias_kind":"arxiv_version","alias_value":"1912.02074v1","created_at":"2026-07-05T00:23:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.02074","created_at":"2026-07-05T00:23:56Z"},{"alias_kind":"pith_short_12","alias_value":"AVH7NMFACIN5","created_at":"2026-07-05T00:23:56Z"},{"alias_kind":"pith_short_16","alias_value":"AVH7NMFACIN5AWTO","created_at":"2026-07-05T00:23:56Z"},{"alias_kind":"pith_short_8","alias_value":"AVH7NMFA","created_at":"2026-07-05T00:23:56Z"}],"graph_snapshots":[{"event_id":"sha256:fac9652d164e95cc2ba9dae76d80289dd57884ec01ff959906f28e83caf401ec","target":"graph","created_at":"2026-07-05T00:23:56Z","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/1912.02074/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In many real-world applications of reinforcement learning (RL), interactions with the environment are limited due to cost or feasibility. This presents a challenge to traditional RL algorithms since the max-return objective involves an expectation over on-policy samples. We introduce a new formulation of max-return optimization that allows the problem to be re-expressed by an expectation over an arbitrary behavior-agnostic and off-policy data distribution. We first derive this result by considering a regularized version of the dual max-return objective before extending our findings to unregula","authors_text":"Bo Dai, Dale Schuurmans, Ilya Kostrikov, Lihong Li, Ofir Nachum, Yinlam Chow","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-04T16:06:10Z","title":"AlgaeDICE: Policy Gradient from Arbitrary Experience"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.02074","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:ae0cdc504f6876e24247cc98a80ad4d36c2fccea3cea95103332be9c72107e32","target":"record","created_at":"2026-07-05T00:23:56Z","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":"e37bcc78139103d45a27227719d963960adef634ac7045d03e21429266ca7029","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-04T16:06:10Z","title_canon_sha256":"9ec97c19b6346ff6625df39d258d4accc4c656f288ae4467c9ffa66b3e8cf2b5"},"schema_version":"1.0","source":{"id":"1912.02074","kind":"arxiv","version":1}},"canonical_sha256":"054ff6b0a0121bd05a6ed90ddef7eb8ffc3ca723af01d580b02d10388fa40c94","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"054ff6b0a0121bd05a6ed90ddef7eb8ffc3ca723af01d580b02d10388fa40c94","first_computed_at":"2026-07-05T00:23:56.650905Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:23:56.650905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HKqQAVSlaDo5IklpZO8qQFPqvIQCQgGUOP4kJi8pxTObC8ZGoKAknoRBzeN90xeODTbSvpPkkgcG5bPdnzrCBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:23:56.651417Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.02074","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae0cdc504f6876e24247cc98a80ad4d36c2fccea3cea95103332be9c72107e32","sha256:fac9652d164e95cc2ba9dae76d80289dd57884ec01ff959906f28e83caf401ec"],"state_sha256":"685cc61dde3ac38383f1f91c9e6ff91f4d793da21bada1546052794a51c2dde7"}