{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5GX2BNK2EJOUACXMFGLVUZENVK","short_pith_number":"pith:5GX2BNK2","schema_version":"1.0","canonical_sha256":"e9afa0b55a225d400aec29975a648daaaac1972e6194152b7540990687d9bd29","source":{"kind":"arxiv","id":"2301.11476","version":4},"attestation_state":"computed","paper":{"title":"Generalized Munchausen Reinforcement Learning using Tsallis KL Divergence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Lingwei Zhu, Martha White, Matthew Schlegel, Zheng Chen","submitted_at":"2023-01-27T00:31:51Z","abstract_excerpt":"Many policy optimization approaches in reinforcement learning incorporate a Kullback-Leilbler (KL) divergence to the previous policy, to prevent the policy from changing too quickly. This idea was initially proposed in a seminal paper on Conservative Policy Iteration, with approximations given by algorithms like TRPO and Munchausen Value Iteration (MVI). We continue this line of work by investigating a generalized KL divergence -- called the Tsallis KL divergence -- which use the $q$-logarithm in the definition. The approach is a strict generalization, as $q = 1$ corresponds to the standard KL"},"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":"2301.11476","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-27T00:31:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c46002f687c2963215f7ae144523344ba2f05449b52a002687321d2ff40344a0","abstract_canon_sha256":"c289dc427844e71ae7c2056828cdb8d51b1726d0608c5499d6391700c6b5130b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:26.236231Z","signature_b64":"eSvrB7NAzzcAVNmw/X953lOyPinXl2cWqSsSKcYFdVShHn0/Z8dPWbwR2YHO1UtYr/BzuFmMr8IIMCTNsRhdCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9afa0b55a225d400aec29975a648daaaac1972e6194152b7540990687d9bd29","last_reissued_at":"2026-07-05T07:57:26.235821Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:26.235821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalized Munchausen Reinforcement Learning using Tsallis KL Divergence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Lingwei Zhu, Martha White, Matthew Schlegel, Zheng Chen","submitted_at":"2023-01-27T00:31:51Z","abstract_excerpt":"Many policy optimization approaches in reinforcement learning incorporate a Kullback-Leilbler (KL) divergence to the previous policy, to prevent the policy from changing too quickly. This idea was initially proposed in a seminal paper on Conservative Policy Iteration, with approximations given by algorithms like TRPO and Munchausen Value Iteration (MVI). We continue this line of work by investigating a generalized KL divergence -- called the Tsallis KL divergence -- which use the $q$-logarithm in the definition. The approach is a strict generalization, as $q = 1$ corresponds to the standard KL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.11476","kind":"arxiv","version":4},"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/2301.11476/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":"2301.11476","created_at":"2026-07-05T07:57:26.235882+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.11476v4","created_at":"2026-07-05T07:57:26.235882+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.11476","created_at":"2026-07-05T07:57:26.235882+00:00"},{"alias_kind":"pith_short_12","alias_value":"5GX2BNK2EJOU","created_at":"2026-07-05T07:57:26.235882+00:00"},{"alias_kind":"pith_short_16","alias_value":"5GX2BNK2EJOUACXM","created_at":"2026-07-05T07:57:26.235882+00:00"},{"alias_kind":"pith_short_8","alias_value":"5GX2BNK2","created_at":"2026-07-05T07:57:26.235882+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/5GX2BNK2EJOUACXMFGLVUZENVK","json":"https://pith.science/pith/5GX2BNK2EJOUACXMFGLVUZENVK.json","graph_json":"https://pith.science/api/pith-number/5GX2BNK2EJOUACXMFGLVUZENVK/graph.json","events_json":"https://pith.science/api/pith-number/5GX2BNK2EJOUACXMFGLVUZENVK/events.json","paper":"https://pith.science/paper/5GX2BNK2"},"agent_actions":{"view_html":"https://pith.science/pith/5GX2BNK2EJOUACXMFGLVUZENVK","download_json":"https://pith.science/pith/5GX2BNK2EJOUACXMFGLVUZENVK.json","view_paper":"https://pith.science/paper/5GX2BNK2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.11476&json=true","fetch_graph":"https://pith.science/api/pith-number/5GX2BNK2EJOUACXMFGLVUZENVK/graph.json","fetch_events":"https://pith.science/api/pith-number/5GX2BNK2EJOUACXMFGLVUZENVK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5GX2BNK2EJOUACXMFGLVUZENVK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5GX2BNK2EJOUACXMFGLVUZENVK/action/storage_attestation","attest_author":"https://pith.science/pith/5GX2BNK2EJOUACXMFGLVUZENVK/action/author_attestation","sign_citation":"https://pith.science/pith/5GX2BNK2EJOUACXMFGLVUZENVK/action/citation_signature","submit_replication":"https://pith.science/pith/5GX2BNK2EJOUACXMFGLVUZENVK/action/replication_record"}},"created_at":"2026-07-05T07:57:26.235882+00:00","updated_at":"2026-07-05T07:57:26.235882+00:00"}