{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VOUZ42BTVBBFNH53HCF374WRYA","short_pith_number":"pith:VOUZ42BT","schema_version":"1.0","canonical_sha256":"aba99e6833a842569fbb388bbff2d1c03907d9e0fe2e571cb80513cc9c962a3b","source":{"kind":"arxiv","id":"2205.07885","version":1},"attestation_state":"computed","paper":{"title":"Enforcing KL Regularization in General Tsallis Entropy Reinforcement Learning via Advantage Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Eiji Uchibe, Lingwei Zhu, Takamitsu Matsubara, Zheng Chen","submitted_at":"2022-05-16T04:47:50Z","abstract_excerpt":"Maximum Tsallis entropy (MTE) framework in reinforcement learning has gained popularity recently by virtue of its flexible modeling choices including the widely used Shannon entropy and sparse entropy. However, non-Shannon entropies suffer from approximation error and subsequent underperformance either due to its sensitivity or the lack of closed-form policy expression. To improve the tradeoff between flexibility and empirical performance, we propose to strengthen their error-robustness by enforcing implicit Kullback-Leibler (KL) regularization in MTE motivated by Munchausen DQN (MDQN). We do "},"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":"2205.07885","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-16T04:47:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3a9d49ef7996aa8d36424c026b3f004e9649f07f8b3463f0648052c836ee9844","abstract_canon_sha256":"4ce138aec1a7d5ca54fd06e1d95ac4fd786fbe38ce3f4e08e403360572eb88c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:23:57.046120Z","signature_b64":"KeYSF0bV/W5CBs0Wx3rijBjBeJ8sLpWC8M2e6uMZBt8Pc0u9Tlnvr3SCkwnqI3+yEpFBfpUvVisiOJHVKjxwDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aba99e6833a842569fbb388bbff2d1c03907d9e0fe2e571cb80513cc9c962a3b","last_reissued_at":"2026-07-05T04:23:57.045720Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:23:57.045720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enforcing KL Regularization in General Tsallis Entropy Reinforcement Learning via Advantage Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Eiji Uchibe, Lingwei Zhu, Takamitsu Matsubara, Zheng Chen","submitted_at":"2022-05-16T04:47:50Z","abstract_excerpt":"Maximum Tsallis entropy (MTE) framework in reinforcement learning has gained popularity recently by virtue of its flexible modeling choices including the widely used Shannon entropy and sparse entropy. However, non-Shannon entropies suffer from approximation error and subsequent underperformance either due to its sensitivity or the lack of closed-form policy expression. To improve the tradeoff between flexibility and empirical performance, we propose to strengthen their error-robustness by enforcing implicit Kullback-Leibler (KL) regularization in MTE motivated by Munchausen DQN (MDQN). We do "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.07885","kind":"arxiv","version":1},"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/2205.07885/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":"2205.07885","created_at":"2026-07-05T04:23:57.045773+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.07885v1","created_at":"2026-07-05T04:23:57.045773+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.07885","created_at":"2026-07-05T04:23:57.045773+00:00"},{"alias_kind":"pith_short_12","alias_value":"VOUZ42BTVBBF","created_at":"2026-07-05T04:23:57.045773+00:00"},{"alias_kind":"pith_short_16","alias_value":"VOUZ42BTVBBFNH53","created_at":"2026-07-05T04:23:57.045773+00:00"},{"alias_kind":"pith_short_8","alias_value":"VOUZ42BT","created_at":"2026-07-05T04:23:57.045773+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/VOUZ42BTVBBFNH53HCF374WRYA","json":"https://pith.science/pith/VOUZ42BTVBBFNH53HCF374WRYA.json","graph_json":"https://pith.science/api/pith-number/VOUZ42BTVBBFNH53HCF374WRYA/graph.json","events_json":"https://pith.science/api/pith-number/VOUZ42BTVBBFNH53HCF374WRYA/events.json","paper":"https://pith.science/paper/VOUZ42BT"},"agent_actions":{"view_html":"https://pith.science/pith/VOUZ42BTVBBFNH53HCF374WRYA","download_json":"https://pith.science/pith/VOUZ42BTVBBFNH53HCF374WRYA.json","view_paper":"https://pith.science/paper/VOUZ42BT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.07885&json=true","fetch_graph":"https://pith.science/api/pith-number/VOUZ42BTVBBFNH53HCF374WRYA/graph.json","fetch_events":"https://pith.science/api/pith-number/VOUZ42BTVBBFNH53HCF374WRYA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VOUZ42BTVBBFNH53HCF374WRYA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VOUZ42BTVBBFNH53HCF374WRYA/action/storage_attestation","attest_author":"https://pith.science/pith/VOUZ42BTVBBFNH53HCF374WRYA/action/author_attestation","sign_citation":"https://pith.science/pith/VOUZ42BTVBBFNH53HCF374WRYA/action/citation_signature","submit_replication":"https://pith.science/pith/VOUZ42BTVBBFNH53HCF374WRYA/action/replication_record"}},"created_at":"2026-07-05T04:23:57.045773+00:00","updated_at":"2026-07-05T04:23:57.045773+00:00"}