{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VORZUQQP5WHBVPM5M7UAUBVGLU","short_pith_number":"pith:VORZUQQP","schema_version":"1.0","canonical_sha256":"aba39a420fed8e1abd9d67e80a06a65d33e31022d737d83ad5c9b6a583b42e08","source":{"kind":"arxiv","id":"2205.07467","version":1},"attestation_state":"computed","paper":{"title":"$q$-Munchausen Reinforcement 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":"2022-05-16T06:26:10Z","abstract_excerpt":"The recently successful Munchausen Reinforcement Learning (M-RL) features implicit Kullback-Leibler (KL) regularization by augmenting the reward function with logarithm of the current stochastic policy. Though significant improvement has been shown with the Boltzmann softmax policy, when the Tsallis sparsemax policy is considered, the augmentation leads to a flat learning curve for almost every problem considered. We show that it is due to the mismatch between the conventional logarithm and the non-logarithmic (generalized) nature of Tsallis entropy. Drawing inspiration from the Tsallis statis"},"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":"2205.07467","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-16T06:26:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"73ec68741f90f6791161c5ee4ff3cacde3531b85bc488246a4a26fd56878786c","abstract_canon_sha256":"8eacd99b107dc1827fdeec616f901f160933e9844380f1ff343536b6f1f04472"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:23:29.375399Z","signature_b64":"m1r1RHIoF8O91HSgYp62CaHTEsFszsqPePVeYjFvrGfZGODrLo6ACEjXtIBqDzVI0oo5j9RQf+nzvA0xazsgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aba39a420fed8e1abd9d67e80a06a65d33e31022d737d83ad5c9b6a583b42e08","last_reissued_at":"2026-07-05T04:23:29.375010Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:23:29.375010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"$q$-Munchausen Reinforcement 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":"2022-05-16T06:26:10Z","abstract_excerpt":"The recently successful Munchausen Reinforcement Learning (M-RL) features implicit Kullback-Leibler (KL) regularization by augmenting the reward function with logarithm of the current stochastic policy. Though significant improvement has been shown with the Boltzmann softmax policy, when the Tsallis sparsemax policy is considered, the augmentation leads to a flat learning curve for almost every problem considered. We show that it is due to the mismatch between the conventional logarithm and the non-logarithmic (generalized) nature of Tsallis entropy. Drawing inspiration from the Tsallis statis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.07467","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/2205.07467/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":"2205.07467","created_at":"2026-07-05T04:23:29.375063+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.07467v1","created_at":"2026-07-05T04:23:29.375063+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.07467","created_at":"2026-07-05T04:23:29.375063+00:00"},{"alias_kind":"pith_short_12","alias_value":"VORZUQQP5WHB","created_at":"2026-07-05T04:23:29.375063+00:00"},{"alias_kind":"pith_short_16","alias_value":"VORZUQQP5WHBVPM5","created_at":"2026-07-05T04:23:29.375063+00:00"},{"alias_kind":"pith_short_8","alias_value":"VORZUQQP","created_at":"2026-07-05T04:23:29.375063+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/VORZUQQP5WHBVPM5M7UAUBVGLU","json":"https://pith.science/pith/VORZUQQP5WHBVPM5M7UAUBVGLU.json","graph_json":"https://pith.science/api/pith-number/VORZUQQP5WHBVPM5M7UAUBVGLU/graph.json","events_json":"https://pith.science/api/pith-number/VORZUQQP5WHBVPM5M7UAUBVGLU/events.json","paper":"https://pith.science/paper/VORZUQQP"},"agent_actions":{"view_html":"https://pith.science/pith/VORZUQQP5WHBVPM5M7UAUBVGLU","download_json":"https://pith.science/pith/VORZUQQP5WHBVPM5M7UAUBVGLU.json","view_paper":"https://pith.science/paper/VORZUQQP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.07467&json=true","fetch_graph":"https://pith.science/api/pith-number/VORZUQQP5WHBVPM5M7UAUBVGLU/graph.json","fetch_events":"https://pith.science/api/pith-number/VORZUQQP5WHBVPM5M7UAUBVGLU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VORZUQQP5WHBVPM5M7UAUBVGLU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VORZUQQP5WHBVPM5M7UAUBVGLU/action/storage_attestation","attest_author":"https://pith.science/pith/VORZUQQP5WHBVPM5M7UAUBVGLU/action/author_attestation","sign_citation":"https://pith.science/pith/VORZUQQP5WHBVPM5M7UAUBVGLU/action/citation_signature","submit_replication":"https://pith.science/pith/VORZUQQP5WHBVPM5M7UAUBVGLU/action/replication_record"}},"created_at":"2026-07-05T04:23:29.375063+00:00","updated_at":"2026-07-05T04:23:29.375063+00:00"}