{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:5SHGPZMLNH7YKDKIHNGMGI6KHI","short_pith_number":"pith:5SHGPZML","canonical_record":{"source":{"id":"1705.07798","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-22T15:06:25Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"34012cc621064e4e53b898ca3a72dab160de80b2c219c0bf5bd94fb289fc0716","abstract_canon_sha256":"942caccdb968f4cb5a9d181a01bbc15016e0a58164c8017cfd187e00b822889c"},"schema_version":"1.0"},"canonical_sha256":"ec8e67e58b69ff850d483b4cc323ca3a34900f8e2738ff3c4f4bf6120482ca37","source":{"kind":"arxiv","id":"1705.07798","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07798","created_at":"2026-05-18T00:44:04Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07798v1","created_at":"2026-05-18T00:44:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07798","created_at":"2026-05-18T00:44:04Z"},{"alias_kind":"pith_short_12","alias_value":"5SHGPZMLNH7Y","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"5SHGPZMLNH7YKDKI","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"5SHGPZML","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:5SHGPZMLNH7YKDKIHNGMGI6KHI","target":"record","payload":{"canonical_record":{"source":{"id":"1705.07798","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-22T15:06:25Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"34012cc621064e4e53b898ca3a72dab160de80b2c219c0bf5bd94fb289fc0716","abstract_canon_sha256":"942caccdb968f4cb5a9d181a01bbc15016e0a58164c8017cfd187e00b822889c"},"schema_version":"1.0"},"canonical_sha256":"ec8e67e58b69ff850d483b4cc323ca3a34900f8e2738ff3c4f4bf6120482ca37","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:04.537166Z","signature_b64":"Q3VBA/ymPpHbMDDdxZ2GCFVAkbJDnFOUtOHWKFsAVPI+HNWO0oz4XJupCgwXEshifIPxipFuSzNJYBO9WmGdAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec8e67e58b69ff850d483b4cc323ca3a34900f8e2738ff3c4f4bf6120482ca37","last_reissued_at":"2026-05-18T00:44:04.536622Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:04.536622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.07798","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":"2026-05-18T00:44:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zfU/ZDMrju1cE6o//TuLtE6l6gomPpA9+R6xyfebtUxzfd+S/xeAdRDL2PCwQkTGb4/F5WG8CtLclTOurLW0Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T22:37:55.679952Z"},"content_sha256":"0963032a2464ed45fb3f7d3cac6a34989149f7e26bf5879793654bbd08ba6c21","schema_version":"1.0","event_id":"sha256:0963032a2464ed45fb3f7d3cac6a34989149f7e26bf5879793654bbd08ba6c21"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:5SHGPZMLNH7YKDKIHNGMGI6KHI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A unified view of entropy-regularized Markov decision processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anders Jonsson, Gergely Neu, Vicen\\c{c} G\\'omez","submitted_at":"2017-05-22T15:06:25Z","abstract_excerpt":"We propose a general framework for entropy-regularized average-reward reinforcement learning in Markov decision processes (MDPs). Our approach is based on extending the linear-programming formulation of policy optimization in MDPs to accommodate convex regularization functions. Our key result is showing that using the conditional entropy of the joint state-action distributions as regularization yields a dual optimization problem closely resembling the Bellman optimality equations. This result enables us to formalize a number of state-of-the-art entropy-regularized reinforcement learning algori"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07798","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":"2026-05-18T00:44:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TVJyfBaB6tF07GOVISoDV+OTtxy+aO/pL8B/x7spgBZiHtHzTgOnliZjKMhNExGY8AHb3ug9rXS2BetZ7frOBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T22:37:55.680652Z"},"content_sha256":"71fef4954f12d0824153a966345753fdebcc30b154e0293c91340276987b5cb5","schema_version":"1.0","event_id":"sha256:71fef4954f12d0824153a966345753fdebcc30b154e0293c91340276987b5cb5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5SHGPZMLNH7YKDKIHNGMGI6KHI/bundle.json","state_url":"https://pith.science/pith/5SHGPZMLNH7YKDKIHNGMGI6KHI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5SHGPZMLNH7YKDKIHNGMGI6KHI/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":"2026-05-31T22:37:55Z","links":{"resolver":"https://pith.science/pith/5SHGPZMLNH7YKDKIHNGMGI6KHI","bundle":"https://pith.science/pith/5SHGPZMLNH7YKDKIHNGMGI6KHI/bundle.json","state":"https://pith.science/pith/5SHGPZMLNH7YKDKIHNGMGI6KHI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5SHGPZMLNH7YKDKIHNGMGI6KHI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:5SHGPZMLNH7YKDKIHNGMGI6KHI","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":"942caccdb968f4cb5a9d181a01bbc15016e0a58164c8017cfd187e00b822889c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-22T15:06:25Z","title_canon_sha256":"34012cc621064e4e53b898ca3a72dab160de80b2c219c0bf5bd94fb289fc0716"},"schema_version":"1.0","source":{"id":"1705.07798","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07798","created_at":"2026-05-18T00:44:04Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07798v1","created_at":"2026-05-18T00:44:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07798","created_at":"2026-05-18T00:44:04Z"},{"alias_kind":"pith_short_12","alias_value":"5SHGPZMLNH7Y","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"5SHGPZMLNH7YKDKI","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"5SHGPZML","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:71fef4954f12d0824153a966345753fdebcc30b154e0293c91340276987b5cb5","target":"graph","created_at":"2026-05-18T00:44:04Z","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 propose a general framework for entropy-regularized average-reward reinforcement learning in Markov decision processes (MDPs). Our approach is based on extending the linear-programming formulation of policy optimization in MDPs to accommodate convex regularization functions. Our key result is showing that using the conditional entropy of the joint state-action distributions as regularization yields a dual optimization problem closely resembling the Bellman optimality equations. This result enables us to formalize a number of state-of-the-art entropy-regularized reinforcement learning algori","authors_text":"Anders Jonsson, Gergely Neu, Vicen\\c{c} G\\'omez","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-22T15:06:25Z","title":"A unified view of entropy-regularized Markov decision processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07798","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":"sha256:0963032a2464ed45fb3f7d3cac6a34989149f7e26bf5879793654bbd08ba6c21","target":"record","created_at":"2026-05-18T00:44:04Z","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":"942caccdb968f4cb5a9d181a01bbc15016e0a58164c8017cfd187e00b822889c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-22T15:06:25Z","title_canon_sha256":"34012cc621064e4e53b898ca3a72dab160de80b2c219c0bf5bd94fb289fc0716"},"schema_version":"1.0","source":{"id":"1705.07798","kind":"arxiv","version":1}},"canonical_sha256":"ec8e67e58b69ff850d483b4cc323ca3a34900f8e2738ff3c4f4bf6120482ca37","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec8e67e58b69ff850d483b4cc323ca3a34900f8e2738ff3c4f4bf6120482ca37","first_computed_at":"2026-05-18T00:44:04.536622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:44:04.536622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q3VBA/ymPpHbMDDdxZ2GCFVAkbJDnFOUtOHWKFsAVPI+HNWO0oz4XJupCgwXEshifIPxipFuSzNJYBO9WmGdAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:44:04.537166Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.07798","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0963032a2464ed45fb3f7d3cac6a34989149f7e26bf5879793654bbd08ba6c21","sha256:71fef4954f12d0824153a966345753fdebcc30b154e0293c91340276987b5cb5"],"state_sha256":"08597c519d209b5436511fb6f3eb33b3add0cf97383c6ba9ca71342ac2084f7a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2zySmBqRP3ubNSDkerqVYi7qNNl1mtNSM+JXOEX0KbiHd26m0LOJS9Lg2DnfFHTmikP2uCEwL2TZthKChnpTBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T22:37:55.684658Z","bundle_sha256":"161edc16cea975fba0dea21c23823adea51a53e05f249f7a4030aac10820611a"}}