{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7QOIJCJ3ZXKEX5WWWSZFZE375C","short_pith_number":"pith:7QOIJCJ3","schema_version":"1.0","canonical_sha256":"fc1c84893bcdd44bf6d6b4b25c937fe8b6c46e8af734c3252501007e06c3bca5","source":{"kind":"arxiv","id":"1912.10891","version":2},"attestation_state":"computed","paper":{"title":"Soft Q Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jingbin Liu, Shuai Liu, Xinyang Gu","submitted_at":"2019-12-20T01:55:40Z","abstract_excerpt":"Deep Q Network (DQN) is a very successful algorithm, yet the inherent problem of reinforcement learning, i.e. the exploit-explore balance, remains. In this work, we introduce entropy regularization into DQN and propose SQN. We find that the backup equation of soft Q learning can enjoy the corrective feedback if we view the soft backup as policy improvement in the form of Q, instead of policy evaluation. We show that Soft Q Learning with Corrective Feedback (SQL-CF) underlies the on-plicy nature of SQL and the equivalence of SQL and Soft Policy Gradient (SPG). With these insights, we propose an"},"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":"1912.10891","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-20T01:55:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e0fd54d0185bee039382ede96bbb23ce9a56e8f419ca2c66c1f025a33e1a9521","abstract_canon_sha256":"e4eb00b2fda2f29454a87a9c082cb818eee985feea0f16d6552eb88af5bc2364"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:59:10.582726Z","signature_b64":"Oo7ru7cDzPabaQs+G9BGbtbmDqBgzSnEDhBZUA8tpZvoouY0vuU7s2A9ad8U617E861PTXk8mtHSuSmDvTZVAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc1c84893bcdd44bf6d6b4b25c937fe8b6c46e8af734c3252501007e06c3bca5","last_reissued_at":"2026-07-05T01:59:10.582236Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:59:10.582236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Soft Q Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jingbin Liu, Shuai Liu, Xinyang Gu","submitted_at":"2019-12-20T01:55:40Z","abstract_excerpt":"Deep Q Network (DQN) is a very successful algorithm, yet the inherent problem of reinforcement learning, i.e. the exploit-explore balance, remains. In this work, we introduce entropy regularization into DQN and propose SQN. We find that the backup equation of soft Q learning can enjoy the corrective feedback if we view the soft backup as policy improvement in the form of Q, instead of policy evaluation. We show that Soft Q Learning with Corrective Feedback (SQL-CF) underlies the on-plicy nature of SQL and the equivalence of SQL and Soft Policy Gradient (SPG). With these insights, we propose an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.10891","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1912.10891/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1912.10891","created_at":"2026-07-05T01:59:10.582294+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.10891v2","created_at":"2026-07-05T01:59:10.582294+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.10891","created_at":"2026-07-05T01:59:10.582294+00:00"},{"alias_kind":"pith_short_12","alias_value":"7QOIJCJ3ZXKE","created_at":"2026-07-05T01:59:10.582294+00:00"},{"alias_kind":"pith_short_16","alias_value":"7QOIJCJ3ZXKEX5WW","created_at":"2026-07-05T01:59:10.582294+00:00"},{"alias_kind":"pith_short_8","alias_value":"7QOIJCJ3","created_at":"2026-07-05T01:59:10.582294+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/7QOIJCJ3ZXKEX5WWWSZFZE375C","json":"https://pith.science/pith/7QOIJCJ3ZXKEX5WWWSZFZE375C.json","graph_json":"https://pith.science/api/pith-number/7QOIJCJ3ZXKEX5WWWSZFZE375C/graph.json","events_json":"https://pith.science/api/pith-number/7QOIJCJ3ZXKEX5WWWSZFZE375C/events.json","paper":"https://pith.science/paper/7QOIJCJ3"},"agent_actions":{"view_html":"https://pith.science/pith/7QOIJCJ3ZXKEX5WWWSZFZE375C","download_json":"https://pith.science/pith/7QOIJCJ3ZXKEX5WWWSZFZE375C.json","view_paper":"https://pith.science/paper/7QOIJCJ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.10891&json=true","fetch_graph":"https://pith.science/api/pith-number/7QOIJCJ3ZXKEX5WWWSZFZE375C/graph.json","fetch_events":"https://pith.science/api/pith-number/7QOIJCJ3ZXKEX5WWWSZFZE375C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7QOIJCJ3ZXKEX5WWWSZFZE375C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7QOIJCJ3ZXKEX5WWWSZFZE375C/action/storage_attestation","attest_author":"https://pith.science/pith/7QOIJCJ3ZXKEX5WWWSZFZE375C/action/author_attestation","sign_citation":"https://pith.science/pith/7QOIJCJ3ZXKEX5WWWSZFZE375C/action/citation_signature","submit_replication":"https://pith.science/pith/7QOIJCJ3ZXKEX5WWWSZFZE375C/action/replication_record"}},"created_at":"2026-07-05T01:59:10.582294+00:00","updated_at":"2026-07-05T01:59:10.582294+00:00"}