{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VOUZ42BTVBBFNH53HCF374WRYA","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":"4ce138aec1a7d5ca54fd06e1d95ac4fd786fbe38ce3f4e08e403360572eb88c3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-16T04:47:50Z","title_canon_sha256":"3a9d49ef7996aa8d36424c026b3f004e9649f07f8b3463f0648052c836ee9844"},"schema_version":"1.0","source":{"id":"2205.07885","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.07885","created_at":"2026-07-05T04:23:57Z"},{"alias_kind":"arxiv_version","alias_value":"2205.07885v1","created_at":"2026-07-05T04:23:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.07885","created_at":"2026-07-05T04:23:57Z"},{"alias_kind":"pith_short_12","alias_value":"VOUZ42BTVBBF","created_at":"2026-07-05T04:23:57Z"},{"alias_kind":"pith_short_16","alias_value":"VOUZ42BTVBBFNH53","created_at":"2026-07-05T04:23:57Z"},{"alias_kind":"pith_short_8","alias_value":"VOUZ42BT","created_at":"2026-07-05T04:23:57Z"}],"graph_snapshots":[{"event_id":"sha256:ce48fd059773a604ed23d9bdfd248de9a84a1d56094d9abc55f94dfa7eadfb5c","target":"graph","created_at":"2026-07-05T04:23:57Z","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/2205.07885/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Eiji Uchibe, Lingwei Zhu, Takamitsu Matsubara, Zheng Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-16T04:47:50Z","title":"Enforcing KL Regularization in General Tsallis Entropy Reinforcement Learning via Advantage Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.07885","kind":"arxiv","version":1},"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":"sha256:186766cb98ff36d75562040f8f732541a5839442b51b75497a6adb8860313923","target":"record","created_at":"2026-07-05T04:23:57Z","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":"4ce138aec1a7d5ca54fd06e1d95ac4fd786fbe38ce3f4e08e403360572eb88c3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-16T04:47:50Z","title_canon_sha256":"3a9d49ef7996aa8d36424c026b3f004e9649f07f8b3463f0648052c836ee9844"},"schema_version":"1.0","source":{"id":"2205.07885","kind":"arxiv","version":1}},"canonical_sha256":"aba99e6833a842569fbb388bbff2d1c03907d9e0fe2e571cb80513cc9c962a3b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aba99e6833a842569fbb388bbff2d1c03907d9e0fe2e571cb80513cc9c962a3b","first_computed_at":"2026-07-05T04:23:57.045720Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:23:57.045720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KeYSF0bV/W5CBs0Wx3rijBjBeJ8sLpWC8M2e6uMZBt8Pc0u9Tlnvr3SCkwnqI3+yEpFBfpUvVisiOJHVKjxwDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:23:57.046120Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.07885","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:186766cb98ff36d75562040f8f732541a5839442b51b75497a6adb8860313923","sha256:ce48fd059773a604ed23d9bdfd248de9a84a1d56094d9abc55f94dfa7eadfb5c"],"state_sha256":"a439167c69f9e469accc2c9fdddf05e720476bccdaf17e3f71c482cce48fb7a6"}