{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:2PMPAG2OCNTDR7NZZGMXMQL63Z","short_pith_number":"pith:2PMPAG2O","schema_version":"1.0","canonical_sha256":"d3d8f01b4e136638fdb9c99976417ede64f26405da65bfb3f3a1b144978d64aa","source":{"kind":"arxiv","id":"1802.03501","version":1},"attestation_state":"computed","paper":{"title":"Path Consistency Learning in Tsallis Entropy Regularized MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Mohammad Ghavamzadeh, Ofir Nachum, Yinlam Chow","submitted_at":"2018-02-10T01:57:49Z","abstract_excerpt":"We study the sparse entropy-regularized reinforcement learning (ERL) problem in which the entropy term is a special form of the Tsallis entropy. The optimal policy of this formulation is sparse, i.e.,~at each state, it has non-zero probability for only a small number of actions. This addresses the main drawback of the standard Shannon entropy-regularized RL (soft ERL) formulation, in which the optimal policy is softmax, and thus, may assign a non-negligible probability mass to non-optimal actions. This problem is aggravated as the number of actions is increased. In this paper, we follow the wo"},"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":"1802.03501","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-10T01:57:49Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"e4baa6c7003bfea944dac52e7abb89ae86e7560428e3e2925ae8415195ce1464","abstract_canon_sha256":"9aebcc74eff73ef48115c3b9ca5f096b98ed535c92ce79f1f218f2fc608dc6e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:51.374332Z","signature_b64":"/CYtXM+eYMuTM26DLNCqCzf6Z63eu1b5PJ5Tvvu1yiKgyReuKl22gOEMM5n/om19gWZOdFB5IznkCDDiHHydAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3d8f01b4e136638fdb9c99976417ede64f26405da65bfb3f3a1b144978d64aa","last_reissued_at":"2026-05-18T00:23:51.373686Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:51.373686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Path Consistency Learning in Tsallis Entropy Regularized MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Mohammad Ghavamzadeh, Ofir Nachum, Yinlam Chow","submitted_at":"2018-02-10T01:57:49Z","abstract_excerpt":"We study the sparse entropy-regularized reinforcement learning (ERL) problem in which the entropy term is a special form of the Tsallis entropy. The optimal policy of this formulation is sparse, i.e.,~at each state, it has non-zero probability for only a small number of actions. This addresses the main drawback of the standard Shannon entropy-regularized RL (soft ERL) formulation, in which the optimal policy is softmax, and thus, may assign a non-negligible probability mass to non-optimal actions. This problem is aggravated as the number of actions is increased. In this paper, we follow the wo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03501","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":""},"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":"1802.03501","created_at":"2026-05-18T00:23:51.373799+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.03501v1","created_at":"2026-05-18T00:23:51.373799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03501","created_at":"2026-05-18T00:23:51.373799+00:00"},{"alias_kind":"pith_short_12","alias_value":"2PMPAG2OCNTD","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"2PMPAG2OCNTDR7NZ","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"2PMPAG2O","created_at":"2026-05-18T12:32:02.567920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.04214","citing_title":"Entropic Regularization of Markov Decision Processes","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2PMPAG2OCNTDR7NZZGMXMQL63Z","json":"https://pith.science/pith/2PMPAG2OCNTDR7NZZGMXMQL63Z.json","graph_json":"https://pith.science/api/pith-number/2PMPAG2OCNTDR7NZZGMXMQL63Z/graph.json","events_json":"https://pith.science/api/pith-number/2PMPAG2OCNTDR7NZZGMXMQL63Z/events.json","paper":"https://pith.science/paper/2PMPAG2O"},"agent_actions":{"view_html":"https://pith.science/pith/2PMPAG2OCNTDR7NZZGMXMQL63Z","download_json":"https://pith.science/pith/2PMPAG2OCNTDR7NZZGMXMQL63Z.json","view_paper":"https://pith.science/paper/2PMPAG2O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.03501&json=true","fetch_graph":"https://pith.science/api/pith-number/2PMPAG2OCNTDR7NZZGMXMQL63Z/graph.json","fetch_events":"https://pith.science/api/pith-number/2PMPAG2OCNTDR7NZZGMXMQL63Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2PMPAG2OCNTDR7NZZGMXMQL63Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2PMPAG2OCNTDR7NZZGMXMQL63Z/action/storage_attestation","attest_author":"https://pith.science/pith/2PMPAG2OCNTDR7NZZGMXMQL63Z/action/author_attestation","sign_citation":"https://pith.science/pith/2PMPAG2OCNTDR7NZZGMXMQL63Z/action/citation_signature","submit_replication":"https://pith.science/pith/2PMPAG2OCNTDR7NZZGMXMQL63Z/action/replication_record"}},"created_at":"2026-05-18T00:23:51.373799+00:00","updated_at":"2026-05-18T00:23:51.373799+00:00"}