{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:PNNI67FEI44DE3HV6UGLEKKS4Q","short_pith_number":"pith:PNNI67FE","schema_version":"1.0","canonical_sha256":"7b5a8f7ca44738326cf5f50cb22952e42c1710b21a71b21d74fc516495c32554","source":{"kind":"arxiv","id":"1901.11275","version":2},"attestation_state":"computed","paper":{"title":"A Theory of Regularized Markov Decision Processes","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bruno Scherrer, Matthieu Geist, Olivier Pietquin","submitted_at":"2019-01-31T09:10:08Z","abstract_excerpt":"Many recent successful (deep) reinforcement learning algorithms make use of regularization, generally based on entropy or Kullback-Leibler divergence. We propose a general theory of regularized Markov Decision Processes that generalizes these approaches in two directions: we consider a larger class of regularizers, and we consider the general modified policy iteration approach, encompassing both policy iteration and value iteration. The core building blocks of this theory are a notion of regularized Bellman operator and the Legendre-Fenchel transform, a classical tool of convex optimization. T"},"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":"1901.11275","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-01-31T09:10:08Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9edeebf007480158a752947a518dbb2b9159359a94b438c40e97ceee65b6fca0","abstract_canon_sha256":"9dded44632b88871697b5be8207b003b20cea6269fd6b7928d5023cc029ebd2a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:21.757794Z","signature_b64":"J258EBipu50GtNLPUYebcL9mxGUnE+yX+SYzV00abm45lMfhHxBmdQN1MSZhEe4nuVkWlHzCUttitryqR2KeCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b5a8f7ca44738326cf5f50cb22952e42c1710b21a71b21d74fc516495c32554","last_reissued_at":"2026-05-17T23:44:21.757085Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:21.757085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Theory of Regularized Markov Decision Processes","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bruno Scherrer, Matthieu Geist, Olivier Pietquin","submitted_at":"2019-01-31T09:10:08Z","abstract_excerpt":"Many recent successful (deep) reinforcement learning algorithms make use of regularization, generally based on entropy or Kullback-Leibler divergence. We propose a general theory of regularized Markov Decision Processes that generalizes these approaches in two directions: we consider a larger class of regularizers, and we consider the general modified policy iteration approach, encompassing both policy iteration and value iteration. The core building blocks of this theory are a notion of regularized Bellman operator and the Legendre-Fenchel transform, a classical tool of convex optimization. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.11275","kind":"arxiv","version":2},"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":"1901.11275","created_at":"2026-05-17T23:44:21.757209+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.11275v2","created_at":"2026-05-17T23:44:21.757209+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.11275","created_at":"2026-05-17T23:44:21.757209+00:00"},{"alias_kind":"pith_short_12","alias_value":"PNNI67FEI44D","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"PNNI67FEI44DE3HV","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"PNNI67FE","created_at":"2026-05-18T12:33:24.271573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.04214","citing_title":"Entropic Regularization of Markov Decision Processes","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19695","citing_title":"Planning in entropy-regularized Markov decision processes and games","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PNNI67FEI44DE3HV6UGLEKKS4Q","json":"https://pith.science/pith/PNNI67FEI44DE3HV6UGLEKKS4Q.json","graph_json":"https://pith.science/api/pith-number/PNNI67FEI44DE3HV6UGLEKKS4Q/graph.json","events_json":"https://pith.science/api/pith-number/PNNI67FEI44DE3HV6UGLEKKS4Q/events.json","paper":"https://pith.science/paper/PNNI67FE"},"agent_actions":{"view_html":"https://pith.science/pith/PNNI67FEI44DE3HV6UGLEKKS4Q","download_json":"https://pith.science/pith/PNNI67FEI44DE3HV6UGLEKKS4Q.json","view_paper":"https://pith.science/paper/PNNI67FE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.11275&json=true","fetch_graph":"https://pith.science/api/pith-number/PNNI67FEI44DE3HV6UGLEKKS4Q/graph.json","fetch_events":"https://pith.science/api/pith-number/PNNI67FEI44DE3HV6UGLEKKS4Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PNNI67FEI44DE3HV6UGLEKKS4Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PNNI67FEI44DE3HV6UGLEKKS4Q/action/storage_attestation","attest_author":"https://pith.science/pith/PNNI67FEI44DE3HV6UGLEKKS4Q/action/author_attestation","sign_citation":"https://pith.science/pith/PNNI67FEI44DE3HV6UGLEKKS4Q/action/citation_signature","submit_replication":"https://pith.science/pith/PNNI67FEI44DE3HV6UGLEKKS4Q/action/replication_record"}},"created_at":"2026-05-17T23:44:21.757209+00:00","updated_at":"2026-05-17T23:44:21.757209+00:00"}