{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:Z2R2HRMJPD7W6RXDKBGANU5USI","short_pith_number":"pith:Z2R2HRMJ","schema_version":"1.0","canonical_sha256":"cea3a3c58978ff6f46e3504c06d3b4923cf653049fd18b676b0aaeb352ae8c47","source":{"kind":"arxiv","id":"1812.00456","version":2},"attestation_state":"computed","paper":{"title":"Revisiting the Softmax Bellman Operator: New Benefits and New Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lawrence Carin, Ronald E. Parr, Zhao Song","submitted_at":"2018-12-02T19:45:38Z","abstract_excerpt":"The impact of softmax on the value function itself in reinforcement learning (RL) is often viewed as problematic because it leads to sub-optimal value (or Q) functions and interferes with the contraction properties of the Bellman operator. Surprisingly, despite these concerns, and independent of its effect on exploration, the softmax Bellman operator when combined with Deep Q-learning, leads to Q-functions with superior policies in practice, even outperforming its double Q-learning counterpart. To better understand how and why this occurs, we revisit theoretical properties of the softmax Bellm"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1812.00456","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-02T19:45:38Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"f66cbf4d0c7ddaf2f0e3ec67175adf62f463db2856e6629b397897e9081e9f5c","abstract_canon_sha256":"2cb596889d95d03e1a3d47d9f4ec9550ca149fca283ce4b74e634463d4d2e1e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:52.447221Z","signature_b64":"oyz3eddG4SgbDRFaIz6aSYjulGddXbUY8fbSy1DPFH/xIQFVnqejIzv8ncIbaruL2h/207QdvPW+3+i/RK7DDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cea3a3c58978ff6f46e3504c06d3b4923cf653049fd18b676b0aaeb352ae8c47","last_reissued_at":"2026-05-17T23:45:52.446699Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:52.446699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting the Softmax Bellman Operator: New Benefits and New Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lawrence Carin, Ronald E. Parr, Zhao Song","submitted_at":"2018-12-02T19:45:38Z","abstract_excerpt":"The impact of softmax on the value function itself in reinforcement learning (RL) is often viewed as problematic because it leads to sub-optimal value (or Q) functions and interferes with the contraction properties of the Bellman operator. Surprisingly, despite these concerns, and independent of its effect on exploration, the softmax Bellman operator when combined with Deep Q-learning, leads to Q-functions with superior policies in practice, even outperforming its double Q-learning counterpart. To better understand how and why this occurs, we revisit theoretical properties of the softmax Bellm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.00456","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1812.00456","created_at":"2026-05-17T23:45:52.446798+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.00456v2","created_at":"2026-05-17T23:45:52.446798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.00456","created_at":"2026-05-17T23:45:52.446798+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z2R2HRMJPD7W","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z2R2HRMJPD7W6RXD","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z2R2HRMJ","created_at":"2026-05-18T12:33:04.347982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z2R2HRMJPD7W6RXDKBGANU5USI","json":"https://pith.science/pith/Z2R2HRMJPD7W6RXDKBGANU5USI.json","graph_json":"https://pith.science/api/pith-number/Z2R2HRMJPD7W6RXDKBGANU5USI/graph.json","events_json":"https://pith.science/api/pith-number/Z2R2HRMJPD7W6RXDKBGANU5USI/events.json","paper":"https://pith.science/paper/Z2R2HRMJ"},"agent_actions":{"view_html":"https://pith.science/pith/Z2R2HRMJPD7W6RXDKBGANU5USI","download_json":"https://pith.science/pith/Z2R2HRMJPD7W6RXDKBGANU5USI.json","view_paper":"https://pith.science/paper/Z2R2HRMJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.00456&json=true","fetch_graph":"https://pith.science/api/pith-number/Z2R2HRMJPD7W6RXDKBGANU5USI/graph.json","fetch_events":"https://pith.science/api/pith-number/Z2R2HRMJPD7W6RXDKBGANU5USI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z2R2HRMJPD7W6RXDKBGANU5USI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z2R2HRMJPD7W6RXDKBGANU5USI/action/storage_attestation","attest_author":"https://pith.science/pith/Z2R2HRMJPD7W6RXDKBGANU5USI/action/author_attestation","sign_citation":"https://pith.science/pith/Z2R2HRMJPD7W6RXDKBGANU5USI/action/citation_signature","submit_replication":"https://pith.science/pith/Z2R2HRMJPD7W6RXDKBGANU5USI/action/replication_record"}},"created_at":"2026-05-17T23:45:52.446798+00:00","updated_at":"2026-05-17T23:45:52.446798+00:00"}