{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:2PMPAG2OCNTDR7NZZGMXMQL63Z","short_pith_number":"pith:2PMPAG2O","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"},"canonical_sha256":"d3d8f01b4e136638fdb9c99976417ede64f26405da65bfb3f3a1b144978d64aa","source":{"kind":"arxiv","id":"1802.03501","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.03501","created_at":"2026-05-18T00:23:51Z"},{"alias_kind":"arxiv_version","alias_value":"1802.03501v1","created_at":"2026-05-18T00:23:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03501","created_at":"2026-05-18T00:23:51Z"},{"alias_kind":"pith_short_12","alias_value":"2PMPAG2OCNTD","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2PMPAG2OCNTDR7NZ","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2PMPAG2O","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:2PMPAG2OCNTDR7NZZGMXMQL63Z","target":"record","payload":{"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"},"canonical_sha256":"d3d8f01b4e136638fdb9c99976417ede64f26405da65bfb3f3a1b144978d64aa","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"},"source_kind":"arxiv","source_id":"1802.03501","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:23:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mTthUFzcEIltzWP4I4mO7XofzRjKqwylg8XN/SX5EdiHfKWTJYoK4RMuneJCB3eOWkRy6oaDgHyx2duWaorzBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T08:48:40.396596Z"},"content_sha256":"6360047cc54a9015e1fc2cacf46486a00c5ea727d7c6cb53136c710982fb1639","schema_version":"1.0","event_id":"sha256:6360047cc54a9015e1fc2cacf46486a00c5ea727d7c6cb53136c710982fb1639"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:2PMPAG2OCNTDR7NZZGMXMQL63Z","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:23:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IxVBZ/dfH7kfZws3i9yraq+vhHADOkcfHtH44fpVCf7z8AyUrOndlvr6kP6Zs5ttbtDaVysiCwo86yMsfLeNAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T08:48:40.397226Z"},"content_sha256":"215d8082a0c06c1b6d7777904c2183c61ff3ede27587c9c7cc0b3de374741ecb","schema_version":"1.0","event_id":"sha256:215d8082a0c06c1b6d7777904c2183c61ff3ede27587c9c7cc0b3de374741ecb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2PMPAG2OCNTDR7NZZGMXMQL63Z/bundle.json","state_url":"https://pith.science/pith/2PMPAG2OCNTDR7NZZGMXMQL63Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2PMPAG2OCNTDR7NZZGMXMQL63Z/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T08:48:40Z","links":{"resolver":"https://pith.science/pith/2PMPAG2OCNTDR7NZZGMXMQL63Z","bundle":"https://pith.science/pith/2PMPAG2OCNTDR7NZZGMXMQL63Z/bundle.json","state":"https://pith.science/pith/2PMPAG2OCNTDR7NZZGMXMQL63Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2PMPAG2OCNTDR7NZZGMXMQL63Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:2PMPAG2OCNTDR7NZZGMXMQL63Z","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":"9aebcc74eff73ef48115c3b9ca5f096b98ed535c92ce79f1f218f2fc608dc6e9","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-10T01:57:49Z","title_canon_sha256":"e4baa6c7003bfea944dac52e7abb89ae86e7560428e3e2925ae8415195ce1464"},"schema_version":"1.0","source":{"id":"1802.03501","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.03501","created_at":"2026-05-18T00:23:51Z"},{"alias_kind":"arxiv_version","alias_value":"1802.03501v1","created_at":"2026-05-18T00:23:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03501","created_at":"2026-05-18T00:23:51Z"},{"alias_kind":"pith_short_12","alias_value":"2PMPAG2OCNTD","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2PMPAG2OCNTDR7NZ","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2PMPAG2O","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:215d8082a0c06c1b6d7777904c2183c61ff3ede27587c9c7cc0b3de374741ecb","target":"graph","created_at":"2026-05-18T00:23:51Z","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"},"paper":{"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","authors_text":"Mohammad Ghavamzadeh, Ofir Nachum, Yinlam Chow","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-10T01:57:49Z","title":"Path Consistency Learning in Tsallis Entropy Regularized MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03501","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":"sha256:6360047cc54a9015e1fc2cacf46486a00c5ea727d7c6cb53136c710982fb1639","target":"record","created_at":"2026-05-18T00:23:51Z","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":"9aebcc74eff73ef48115c3b9ca5f096b98ed535c92ce79f1f218f2fc608dc6e9","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-10T01:57:49Z","title_canon_sha256":"e4baa6c7003bfea944dac52e7abb89ae86e7560428e3e2925ae8415195ce1464"},"schema_version":"1.0","source":{"id":"1802.03501","kind":"arxiv","version":1}},"canonical_sha256":"d3d8f01b4e136638fdb9c99976417ede64f26405da65bfb3f3a1b144978d64aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3d8f01b4e136638fdb9c99976417ede64f26405da65bfb3f3a1b144978d64aa","first_computed_at":"2026-05-18T00:23:51.373686Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:23:51.373686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/CYtXM+eYMuTM26DLNCqCzf6Z63eu1b5PJ5Tvvu1yiKgyReuKl22gOEMM5n/om19gWZOdFB5IznkCDDiHHydAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:23:51.374332Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.03501","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6360047cc54a9015e1fc2cacf46486a00c5ea727d7c6cb53136c710982fb1639","sha256:215d8082a0c06c1b6d7777904c2183c61ff3ede27587c9c7cc0b3de374741ecb"],"state_sha256":"4515e7a2160543a6184f3f22974bde7999e9980d36474a22e0462ecb525e78b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8a8X8KwFJoE9UYOmA5hgyidI52uEpnysko4nzC5ljeITTE/4cCWZuNR/bV9vukcAYHf8bXlRFnY5JHJcaBX5DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T08:48:40.400657Z","bundle_sha256":"1601413cec1dbfac284f78dde60af786bd06a62adf1653636ddb4dddf947ea38"}}