{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:AWKA5HZUEB2IC6SCFWBK5SQS6G","short_pith_number":"pith:AWKA5HZU","canonical_record":{"source":{"id":"1510.04454","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-10-15T09:19:49Z","cross_cats_sorted":[],"title_canon_sha256":"7e4edc5a8b8a05ecb2385fda2f86d35c946467cb87af1fb3cd78f56da166763f","abstract_canon_sha256":"84bafd81230c4e50a38e3630783bd5024eeabf95c7043a633b91740b23f7acc5"},"schema_version":"1.0"},"canonical_sha256":"05940e9f342074817a422d82aeca12f1a78142f6359c8fc69d191da42e204712","source":{"kind":"arxiv","id":"1510.04454","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1510.04454","created_at":"2026-05-18T01:30:07Z"},{"alias_kind":"arxiv_version","alias_value":"1510.04454v1","created_at":"2026-05-18T01:30:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.04454","created_at":"2026-05-18T01:30:07Z"},{"alias_kind":"pith_short_12","alias_value":"AWKA5HZUEB2I","created_at":"2026-05-18T12:29:10Z"},{"alias_kind":"pith_short_16","alias_value":"AWKA5HZUEB2IC6SC","created_at":"2026-05-18T12:29:10Z"},{"alias_kind":"pith_short_8","alias_value":"AWKA5HZU","created_at":"2026-05-18T12:29:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:AWKA5HZUEB2IC6SCFWBK5SQS6G","target":"record","payload":{"canonical_record":{"source":{"id":"1510.04454","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-10-15T09:19:49Z","cross_cats_sorted":[],"title_canon_sha256":"7e4edc5a8b8a05ecb2385fda2f86d35c946467cb87af1fb3cd78f56da166763f","abstract_canon_sha256":"84bafd81230c4e50a38e3630783bd5024eeabf95c7043a633b91740b23f7acc5"},"schema_version":"1.0"},"canonical_sha256":"05940e9f342074817a422d82aeca12f1a78142f6359c8fc69d191da42e204712","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:30:07.136869Z","signature_b64":"v46kM/fUPh3ypz5uoaRfhYOqO58A+viXkbEajG+EhnuA9kcHCTjD6pSM8iw5fDmPE422fxgkmOzSgaqhnsO+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05940e9f342074817a422d82aeca12f1a78142f6359c8fc69d191da42e204712","last_reissued_at":"2026-05-18T01:30:07.136407Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:30:07.136407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1510.04454","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":"2026-05-18T01:30:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PcSWbKYzXit6NK60wSeAJnHgQC4+pSrIKV1OBAEWYfe7pp1nTnvEcanzbGWG0gQkFS7P6sW1Li9nbhKMBKCECw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T23:47:21.286508Z"},"content_sha256":"b9f061649c80299ae5bfa64ac845f98e08330890766d12448ab21d7966ceeec2","schema_version":"1.0","event_id":"sha256:b9f061649c80299ae5bfa64ac845f98e08330890766d12448ab21d7966ceeec2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:AWKA5HZUEB2IC6SCFWBK5SQS6G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Online Markov decision processes with policy iteration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hao Zhang, Masashi Sugiyama, Yao Ma","submitted_at":"2015-10-15T09:19:49Z","abstract_excerpt":"The online Markov decision process (MDP) is a generalization of the classical Markov decision process that incorporates changing reward functions. In this paper, we propose practical online MDP algorithms with policy iteration and theoretically establish a sublinear regret bound. A notable advantage of the proposed algorithm is that it can be easily combined with function approximation, and thus large and possibly continuous state spaces can be efficiently handled. Through experiments, we demonstrate the usefulness of the proposed algorithm."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.04454","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":"2026-05-18T01:30:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a4coDwL51mAbhJse9B3HiiHxGWbtPhA1La4gceNUaMYDdRuHvtgkvGOo7MIgXrbmLEeQcCS60kQK6rkFt1ceAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T23:47:21.286849Z"},"content_sha256":"826eedf938ad2fec86f93cb77063a7f03ee4b9cb532b7000cb742ab0c52e0e88","schema_version":"1.0","event_id":"sha256:826eedf938ad2fec86f93cb77063a7f03ee4b9cb532b7000cb742ab0c52e0e88"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AWKA5HZUEB2IC6SCFWBK5SQS6G/bundle.json","state_url":"https://pith.science/pith/AWKA5HZUEB2IC6SCFWBK5SQS6G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AWKA5HZUEB2IC6SCFWBK5SQS6G/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":"2026-06-08T23:47:21Z","links":{"resolver":"https://pith.science/pith/AWKA5HZUEB2IC6SCFWBK5SQS6G","bundle":"https://pith.science/pith/AWKA5HZUEB2IC6SCFWBK5SQS6G/bundle.json","state":"https://pith.science/pith/AWKA5HZUEB2IC6SCFWBK5SQS6G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AWKA5HZUEB2IC6SCFWBK5SQS6G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:AWKA5HZUEB2IC6SCFWBK5SQS6G","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":"84bafd81230c4e50a38e3630783bd5024eeabf95c7043a633b91740b23f7acc5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-10-15T09:19:49Z","title_canon_sha256":"7e4edc5a8b8a05ecb2385fda2f86d35c946467cb87af1fb3cd78f56da166763f"},"schema_version":"1.0","source":{"id":"1510.04454","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1510.04454","created_at":"2026-05-18T01:30:07Z"},{"alias_kind":"arxiv_version","alias_value":"1510.04454v1","created_at":"2026-05-18T01:30:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.04454","created_at":"2026-05-18T01:30:07Z"},{"alias_kind":"pith_short_12","alias_value":"AWKA5HZUEB2I","created_at":"2026-05-18T12:29:10Z"},{"alias_kind":"pith_short_16","alias_value":"AWKA5HZUEB2IC6SC","created_at":"2026-05-18T12:29:10Z"},{"alias_kind":"pith_short_8","alias_value":"AWKA5HZU","created_at":"2026-05-18T12:29:10Z"}],"graph_snapshots":[{"event_id":"sha256:826eedf938ad2fec86f93cb77063a7f03ee4b9cb532b7000cb742ab0c52e0e88","target":"graph","created_at":"2026-05-18T01:30:07Z","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":"The online Markov decision process (MDP) is a generalization of the classical Markov decision process that incorporates changing reward functions. In this paper, we propose practical online MDP algorithms with policy iteration and theoretically establish a sublinear regret bound. A notable advantage of the proposed algorithm is that it can be easily combined with function approximation, and thus large and possibly continuous state spaces can be efficiently handled. Through experiments, we demonstrate the usefulness of the proposed algorithm.","authors_text":"Hao Zhang, Masashi Sugiyama, Yao Ma","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-10-15T09:19:49Z","title":"Online Markov decision processes with policy iteration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.04454","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:b9f061649c80299ae5bfa64ac845f98e08330890766d12448ab21d7966ceeec2","target":"record","created_at":"2026-05-18T01:30:07Z","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":"84bafd81230c4e50a38e3630783bd5024eeabf95c7043a633b91740b23f7acc5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-10-15T09:19:49Z","title_canon_sha256":"7e4edc5a8b8a05ecb2385fda2f86d35c946467cb87af1fb3cd78f56da166763f"},"schema_version":"1.0","source":{"id":"1510.04454","kind":"arxiv","version":1}},"canonical_sha256":"05940e9f342074817a422d82aeca12f1a78142f6359c8fc69d191da42e204712","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"05940e9f342074817a422d82aeca12f1a78142f6359c8fc69d191da42e204712","first_computed_at":"2026-05-18T01:30:07.136407Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:30:07.136407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v46kM/fUPh3ypz5uoaRfhYOqO58A+viXkbEajG+EhnuA9kcHCTjD6pSM8iw5fDmPE422fxgkmOzSgaqhnsO+DA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:30:07.136869Z","signed_message":"canonical_sha256_bytes"},"source_id":"1510.04454","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b9f061649c80299ae5bfa64ac845f98e08330890766d12448ab21d7966ceeec2","sha256:826eedf938ad2fec86f93cb77063a7f03ee4b9cb532b7000cb742ab0c52e0e88"],"state_sha256":"68a6c58bac86bb8aa0c31b55d524ba1384ed45ce43db9a7a7d0f19f70689f321"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vqa0LGk65Nwf/zqOgcOqaSAvzvwqo6CFHCZdB8JL8ut3EFfSrh0n8CcrpM9KdOOOzqPR8l/7EkV0Lm14POPLBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T23:47:21.288674Z","bundle_sha256":"ab6b99e0286c6834b48b8919c287eed69997466f0612653584dcd75158b93d77"}}