{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:47UYL6ELR4RW55RHNURRYDIAPS","short_pith_number":"pith:47UYL6EL","schema_version":"1.0","canonical_sha256":"e7e985f88b8f236ef6276d231c0d007c9fd3ffab85ad12f4715f5ad37d022489","source":{"kind":"arxiv","id":"2112.15364","version":1},"attestation_state":"computed","paper":{"title":"Robust Entropy-regularized Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Patrick Jaillet, Tien Mai","submitted_at":"2021-12-31T09:50:46Z","abstract_excerpt":"Stochastic and soft optimal policies resulting from entropy-regularized Markov decision processes (ER-MDP) are desirable for exploration and imitation learning applications. Motivated by the fact that such policies are sensitive with respect to the state transition probabilities, and the estimation of these probabilities may be inaccurate, we study a robust version of the ER-MDP model, where the stochastic optimal policies are required to be robust with respect to the ambiguity in the underlying transition probabilities. Our work is at the crossroads of two important schemes in reinforcement l"},"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":"2112.15364","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-31T09:50:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bd334c55d5022d100333993d9e5b4025fe6dde0f2fdb38d49231560c62c8bc42","abstract_canon_sha256":"f37f3aff1048a9a0c17dbc33c019d611f88a3e615a798e8945bf23ea2e91fc1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:44:39.386450Z","signature_b64":"MiyHKqkfrgn2VW3OHn3MrLgRqNkmeaesZF+Ue/xwys1IEL+o9FbDGrEWMr21ZU4aXTK9UmDSudbCq9WMRL7GBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7e985f88b8f236ef6276d231c0d007c9fd3ffab85ad12f4715f5ad37d022489","last_reissued_at":"2026-07-05T03:44:39.386019Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:44:39.386019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Entropy-regularized Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Patrick Jaillet, Tien Mai","submitted_at":"2021-12-31T09:50:46Z","abstract_excerpt":"Stochastic and soft optimal policies resulting from entropy-regularized Markov decision processes (ER-MDP) are desirable for exploration and imitation learning applications. Motivated by the fact that such policies are sensitive with respect to the state transition probabilities, and the estimation of these probabilities may be inaccurate, we study a robust version of the ER-MDP model, where the stochastic optimal policies are required to be robust with respect to the ambiguity in the underlying transition probabilities. Our work is at the crossroads of two important schemes in reinforcement l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.15364","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/2112.15364/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":"2112.15364","created_at":"2026-07-05T03:44:39.386077+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.15364v1","created_at":"2026-07-05T03:44:39.386077+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.15364","created_at":"2026-07-05T03:44:39.386077+00:00"},{"alias_kind":"pith_short_12","alias_value":"47UYL6ELR4RW","created_at":"2026-07-05T03:44:39.386077+00:00"},{"alias_kind":"pith_short_16","alias_value":"47UYL6ELR4RW55RH","created_at":"2026-07-05T03:44:39.386077+00:00"},{"alias_kind":"pith_short_8","alias_value":"47UYL6EL","created_at":"2026-07-05T03:44:39.386077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.16286","citing_title":"Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/47UYL6ELR4RW55RHNURRYDIAPS","json":"https://pith.science/pith/47UYL6ELR4RW55RHNURRYDIAPS.json","graph_json":"https://pith.science/api/pith-number/47UYL6ELR4RW55RHNURRYDIAPS/graph.json","events_json":"https://pith.science/api/pith-number/47UYL6ELR4RW55RHNURRYDIAPS/events.json","paper":"https://pith.science/paper/47UYL6EL"},"agent_actions":{"view_html":"https://pith.science/pith/47UYL6ELR4RW55RHNURRYDIAPS","download_json":"https://pith.science/pith/47UYL6ELR4RW55RHNURRYDIAPS.json","view_paper":"https://pith.science/paper/47UYL6EL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.15364&json=true","fetch_graph":"https://pith.science/api/pith-number/47UYL6ELR4RW55RHNURRYDIAPS/graph.json","fetch_events":"https://pith.science/api/pith-number/47UYL6ELR4RW55RHNURRYDIAPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/47UYL6ELR4RW55RHNURRYDIAPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/47UYL6ELR4RW55RHNURRYDIAPS/action/storage_attestation","attest_author":"https://pith.science/pith/47UYL6ELR4RW55RHNURRYDIAPS/action/author_attestation","sign_citation":"https://pith.science/pith/47UYL6ELR4RW55RHNURRYDIAPS/action/citation_signature","submit_replication":"https://pith.science/pith/47UYL6ELR4RW55RHNURRYDIAPS/action/replication_record"}},"created_at":"2026-07-05T03:44:39.386077+00:00","updated_at":"2026-07-05T03:44:39.386077+00:00"}