{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:PNNI67FEI44DE3HV6UGLEKKS4Q","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":"9dded44632b88871697b5be8207b003b20cea6269fd6b7928d5023cc029ebd2a","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-01-31T09:10:08Z","title_canon_sha256":"9edeebf007480158a752947a518dbb2b9159359a94b438c40e97ceee65b6fca0"},"schema_version":"1.0","source":{"id":"1901.11275","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.11275","created_at":"2026-05-17T23:44:21Z"},{"alias_kind":"arxiv_version","alias_value":"1901.11275v2","created_at":"2026-05-17T23:44:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.11275","created_at":"2026-05-17T23:44:21Z"},{"alias_kind":"pith_short_12","alias_value":"PNNI67FEI44D","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"PNNI67FEI44DE3HV","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"PNNI67FE","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:d603c8db36d01dcf299b485403da5dea54074ed44f864ec7e338055cd3ebbd06","target":"graph","created_at":"2026-05-17T23:44:21Z","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":"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","authors_text":"Bruno Scherrer, Matthieu Geist, Olivier Pietquin","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-01-31T09:10:08Z","title":"A Theory of Regularized Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.11275","kind":"arxiv","version":2},"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:ca863958375a343b6caf8a7c0ea22e1b71820b3db67ea65019aada89541213b9","target":"record","created_at":"2026-05-17T23:44:21Z","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":"9dded44632b88871697b5be8207b003b20cea6269fd6b7928d5023cc029ebd2a","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-01-31T09:10:08Z","title_canon_sha256":"9edeebf007480158a752947a518dbb2b9159359a94b438c40e97ceee65b6fca0"},"schema_version":"1.0","source":{"id":"1901.11275","kind":"arxiv","version":2}},"canonical_sha256":"7b5a8f7ca44738326cf5f50cb22952e42c1710b21a71b21d74fc516495c32554","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b5a8f7ca44738326cf5f50cb22952e42c1710b21a71b21d74fc516495c32554","first_computed_at":"2026-05-17T23:44:21.757085Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:21.757085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J258EBipu50GtNLPUYebcL9mxGUnE+yX+SYzV00abm45lMfhHxBmdQN1MSZhEe4nuVkWlHzCUttitryqR2KeCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:21.757794Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.11275","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca863958375a343b6caf8a7c0ea22e1b71820b3db67ea65019aada89541213b9","sha256:d603c8db36d01dcf299b485403da5dea54074ed44f864ec7e338055cd3ebbd06"],"state_sha256":"ea1f94f4fecc197a01f6e853b79a12be3de04adb1699651e25e73670fbcb96ac"}