{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:WID7QOXWKJQE35BICP3WHMYKGE","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":"e682ec0312b2966f5d374f8fd8944fba1fd2aa3461951d86feb5af743fc4749c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-21T08:33:59Z","title_canon_sha256":"d6232e35a531cd153c7eaa31b02e103c5638dbe733f4cdb0f7402562843b3390"},"schema_version":"1.0","source":{"id":"1704.06440","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.06440","created_at":"2026-05-18T00:03:25Z"},{"alias_kind":"arxiv_version","alias_value":"1704.06440v4","created_at":"2026-05-18T00:03:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.06440","created_at":"2026-05-18T00:03:25Z"},{"alias_kind":"pith_short_12","alias_value":"WID7QOXWKJQE","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WID7QOXWKJQE35BI","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WID7QOXW","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:52badd1ac6a0586e60ed2e1b42edc5c956d668edc8a2bb2704452291ecd569fd","target":"graph","created_at":"2026-05-18T00:03:25Z","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"},"paper":{"abstract_excerpt":"Two of the leading approaches for model-free reinforcement learning are policy gradient methods and $Q$-learning methods. $Q$-learning methods can be effective and sample-efficient when they work, however, it is not well-understood why they work, since empirically, the $Q$-values they estimate are very inaccurate. A partial explanation may be that $Q$-learning methods are secretly implementing policy gradient updates: we show that there is a precise equivalence between $Q$-learning and policy gradient methods in the setting of entropy-regularized reinforcement learning, that \"soft\" (entropy-re","authors_text":"John Schulman, Pieter Abbeel, Xi Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-21T08:33:59Z","title":"Equivalence Between Policy Gradients and Soft Q-Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.06440","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:c8e3421b8251f0ee488fb3bf90451eca32a5912f8a07e32bf30dc5940cfc33c3","target":"record","created_at":"2026-05-18T00:03:25Z","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":"e682ec0312b2966f5d374f8fd8944fba1fd2aa3461951d86feb5af743fc4749c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-21T08:33:59Z","title_canon_sha256":"d6232e35a531cd153c7eaa31b02e103c5638dbe733f4cdb0f7402562843b3390"},"schema_version":"1.0","source":{"id":"1704.06440","kind":"arxiv","version":4}},"canonical_sha256":"b207f83af652604df42813f763b30a3125ee0b196676c3ead9123dfe78b4f6ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b207f83af652604df42813f763b30a3125ee0b196676c3ead9123dfe78b4f6ce","first_computed_at":"2026-05-18T00:03:25.093186Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:03:25.093186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Sf+wvu2W3AvqOBjOcVAfmEhxX3Ud2MEskcwB31t1gjM86plnw2JJsn//Jzha+/thJtp35vymF/rHAgZzRYExBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:03:25.093694Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.06440","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8e3421b8251f0ee488fb3bf90451eca32a5912f8a07e32bf30dc5940cfc33c3","sha256:52badd1ac6a0586e60ed2e1b42edc5c956d668edc8a2bb2704452291ecd569fd"],"state_sha256":"b62113e9addc39a89a1d0bac5a639d2cc7e29668150f6cd23861d4b0d94e9e55"}