{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:YF3PJTJBU74UMBDLHRXAMCZ2QP","short_pith_number":"pith:YF3PJTJB","canonical_record":{"source":{"id":"1907.04214","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-07-06T15:02:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"95a53f46d3aee2ae6c37fa84d688e5a12c8ff55c112f3b66215202ef8979c660","abstract_canon_sha256":"4adfa88c755e9d912e43b4dadea1a56e66137499f943515af0c8b4043b306a3d"},"schema_version":"1.0"},"canonical_sha256":"c176f4cd21a7f946046b3c6e060b3a83e0b73486f0c97301e8f73979004b4a6f","source":{"kind":"arxiv","id":"1907.04214","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.04214","created_at":"2026-05-17T23:40:16Z"},{"alias_kind":"arxiv_version","alias_value":"1907.04214v2","created_at":"2026-05-17T23:40:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.04214","created_at":"2026-05-17T23:40:16Z"},{"alias_kind":"pith_short_12","alias_value":"YF3PJTJBU74U","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"YF3PJTJBU74UMBDL","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"YF3PJTJB","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:YF3PJTJBU74UMBDLHRXAMCZ2QP","target":"record","payload":{"canonical_record":{"source":{"id":"1907.04214","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-07-06T15:02:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"95a53f46d3aee2ae6c37fa84d688e5a12c8ff55c112f3b66215202ef8979c660","abstract_canon_sha256":"4adfa88c755e9d912e43b4dadea1a56e66137499f943515af0c8b4043b306a3d"},"schema_version":"1.0"},"canonical_sha256":"c176f4cd21a7f946046b3c6e060b3a83e0b73486f0c97301e8f73979004b4a6f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:16.996943Z","signature_b64":"ajBtRQOfLIFL9NYVgQNv2pkx5/kB4SDdreIqO4qdSXPNbNNk/tMv0Ep6HfQh08odAEyXxdgHLmX1jf4RQwlpAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c176f4cd21a7f946046b3c6e060b3a83e0b73486f0c97301e8f73979004b4a6f","last_reissued_at":"2026-05-17T23:40:16.995977Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:16.995977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.04214","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:40:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NIqcjPkNxHXKaDSFxfWl8mC4xHDywYXcINj2Cvbm27exq3qIFP7ZcjXo9o4Skp8uESHE1BpBtNPDDCT3RvA2Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T21:55:25.810672Z"},"content_sha256":"27969eb5c27c7a71eeab7c64d6199758764678f7b3fc93bf0881753353315e51","schema_version":"1.0","event_id":"sha256:27969eb5c27c7a71eeab7c64d6199758764678f7b3fc93bf0881753353315e51"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:YF3PJTJBU74UMBDLHRXAMCZ2QP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Entropic Regularization of Markov Decision Processes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Boris Belousov, Jan Peters","submitted_at":"2019-07-06T15:02:56Z","abstract_excerpt":"An optimal feedback controller for a given Markov decision process (MDP) can in principle be synthesized by value or policy iteration. However, if the system dynamics and the reward function are unknown, a learning agent must discover an optimal controller via direct interaction with the environment. Such interactive data gathering commonly leads to divergence towards dangerous or uninformative regions of the state space unless additional regularization measures are taken. Prior works proposed bounding the information loss measured by the Kullback-Leibler (KL) divergence at every policy improv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.04214","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:40:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tDn8t1qsuABxFFW8nIFcEuT8W7So3fyDVG/FCh2JveBAvpLgShP0zrb0m7PqYycf7RDzuXcGfnBhP71a9VHiBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T21:55:25.811260Z"},"content_sha256":"ae845b79eea9d176c2de3521152a8b18261d9a4fbcd651f13435fc922cecbd30","schema_version":"1.0","event_id":"sha256:ae845b79eea9d176c2de3521152a8b18261d9a4fbcd651f13435fc922cecbd30"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YF3PJTJBU74UMBDLHRXAMCZ2QP/bundle.json","state_url":"https://pith.science/pith/YF3PJTJBU74UMBDLHRXAMCZ2QP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YF3PJTJBU74UMBDLHRXAMCZ2QP/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":"2026-05-18T21:55:25Z","links":{"resolver":"https://pith.science/pith/YF3PJTJBU74UMBDLHRXAMCZ2QP","bundle":"https://pith.science/pith/YF3PJTJBU74UMBDLHRXAMCZ2QP/bundle.json","state":"https://pith.science/pith/YF3PJTJBU74UMBDLHRXAMCZ2QP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YF3PJTJBU74UMBDLHRXAMCZ2QP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:YF3PJTJBU74UMBDLHRXAMCZ2QP","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":"4adfa88c755e9d912e43b4dadea1a56e66137499f943515af0c8b4043b306a3d","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-07-06T15:02:56Z","title_canon_sha256":"95a53f46d3aee2ae6c37fa84d688e5a12c8ff55c112f3b66215202ef8979c660"},"schema_version":"1.0","source":{"id":"1907.04214","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.04214","created_at":"2026-05-17T23:40:16Z"},{"alias_kind":"arxiv_version","alias_value":"1907.04214v2","created_at":"2026-05-17T23:40:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.04214","created_at":"2026-05-17T23:40:16Z"},{"alias_kind":"pith_short_12","alias_value":"YF3PJTJBU74U","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"YF3PJTJBU74UMBDL","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"YF3PJTJB","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:ae845b79eea9d176c2de3521152a8b18261d9a4fbcd651f13435fc922cecbd30","target":"graph","created_at":"2026-05-17T23:40:16Z","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":"An optimal feedback controller for a given Markov decision process (MDP) can in principle be synthesized by value or policy iteration. However, if the system dynamics and the reward function are unknown, a learning agent must discover an optimal controller via direct interaction with the environment. Such interactive data gathering commonly leads to divergence towards dangerous or uninformative regions of the state space unless additional regularization measures are taken. Prior works proposed bounding the information loss measured by the Kullback-Leibler (KL) divergence at every policy improv","authors_text":"Boris Belousov, Jan Peters","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-07-06T15:02:56Z","title":"Entropic Regularization of Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.04214","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":"sha256:27969eb5c27c7a71eeab7c64d6199758764678f7b3fc93bf0881753353315e51","target":"record","created_at":"2026-05-17T23:40:16Z","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":"4adfa88c755e9d912e43b4dadea1a56e66137499f943515af0c8b4043b306a3d","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-07-06T15:02:56Z","title_canon_sha256":"95a53f46d3aee2ae6c37fa84d688e5a12c8ff55c112f3b66215202ef8979c660"},"schema_version":"1.0","source":{"id":"1907.04214","kind":"arxiv","version":2}},"canonical_sha256":"c176f4cd21a7f946046b3c6e060b3a83e0b73486f0c97301e8f73979004b4a6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c176f4cd21a7f946046b3c6e060b3a83e0b73486f0c97301e8f73979004b4a6f","first_computed_at":"2026-05-17T23:40:16.995977Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:40:16.995977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ajBtRQOfLIFL9NYVgQNv2pkx5/kB4SDdreIqO4qdSXPNbNNk/tMv0Ep6HfQh08odAEyXxdgHLmX1jf4RQwlpAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:40:16.996943Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.04214","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27969eb5c27c7a71eeab7c64d6199758764678f7b3fc93bf0881753353315e51","sha256:ae845b79eea9d176c2de3521152a8b18261d9a4fbcd651f13435fc922cecbd30"],"state_sha256":"ef75d98e25b5b7b50edb5aab521f355a5792aeed459c94f588a398854388515e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T5+w5i6+sgOYxZ74+PDlC6y71JBTfl3fU4MdPK0jzKGMuZey3Qnc5y5MpX96D6aJV1eDn7E3SWza6v3ZIQpFBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-18T21:55:25.813155Z","bundle_sha256":"e001764a90a7816bae4a0eabfc631e5d65a636ef63bd5ec421d237cea53b047c"}}