{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7QOIJCJ3ZXKEX5WWWSZFZE375C","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":"e4eb00b2fda2f29454a87a9c082cb818eee985feea0f16d6552eb88af5bc2364","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-20T01:55:40Z","title_canon_sha256":"e0fd54d0185bee039382ede96bbb23ce9a56e8f419ca2c66c1f025a33e1a9521"},"schema_version":"1.0","source":{"id":"1912.10891","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.10891","created_at":"2026-07-05T01:59:10Z"},{"alias_kind":"arxiv_version","alias_value":"1912.10891v2","created_at":"2026-07-05T01:59:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.10891","created_at":"2026-07-05T01:59:10Z"},{"alias_kind":"pith_short_12","alias_value":"7QOIJCJ3ZXKE","created_at":"2026-07-05T01:59:10Z"},{"alias_kind":"pith_short_16","alias_value":"7QOIJCJ3ZXKEX5WW","created_at":"2026-07-05T01:59:10Z"},{"alias_kind":"pith_short_8","alias_value":"7QOIJCJ3","created_at":"2026-07-05T01:59:10Z"}],"graph_snapshots":[{"event_id":"sha256:504562a8a559b2a0490fea8211076b21d37558a9bd3233c0ee7ae799f9a471a8","target":"graph","created_at":"2026-07-05T01:59:10Z","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/1912.10891/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jingbin Liu, Shuai Liu, Xinyang Gu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-20T01:55:40Z","title":"Soft Q Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.10891","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":"sha256:14bbaaa39ebac739b0df4e15a7d9cc5cfc2434456af8687ebdc17c6a62126be5","target":"record","created_at":"2026-07-05T01:59:10Z","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":"e4eb00b2fda2f29454a87a9c082cb818eee985feea0f16d6552eb88af5bc2364","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-20T01:55:40Z","title_canon_sha256":"e0fd54d0185bee039382ede96bbb23ce9a56e8f419ca2c66c1f025a33e1a9521"},"schema_version":"1.0","source":{"id":"1912.10891","kind":"arxiv","version":2}},"canonical_sha256":"fc1c84893bcdd44bf6d6b4b25c937fe8b6c46e8af734c3252501007e06c3bca5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc1c84893bcdd44bf6d6b4b25c937fe8b6c46e8af734c3252501007e06c3bca5","first_computed_at":"2026-07-05T01:59:10.582236Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:59:10.582236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Oo7ru7cDzPabaQs+G9BGbtbmDqBgzSnEDhBZUA8tpZvoouY0vuU7s2A9ad8U617E861PTXk8mtHSuSmDvTZVAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:59:10.582726Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.10891","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14bbaaa39ebac739b0df4e15a7d9cc5cfc2434456af8687ebdc17c6a62126be5","sha256:504562a8a559b2a0490fea8211076b21d37558a9bd3233c0ee7ae799f9a471a8"],"state_sha256":"893018f5fab9b2629ccbbcc81173d6eb1a8f8ded3af5b644e0db6780ca13c396"}