{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:IEKUQJ7RE6RJHTMHHI5LUEYSED","short_pith_number":"pith:IEKUQJ7R","canonical_record":{"source":{"id":"1905.07773","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-19T16:56:22Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"b9408c0196c076c0f0df845828c5c1e97399310f0a7ccc553a035f1d920ccd3c","abstract_canon_sha256":"fad5753896208086edafd3051e510f386c3e5e9932dbd008ecef16687d0f8ef6"},"schema_version":"1.0"},"canonical_sha256":"41154827f127a293cd873a3aba131220dbeea4457c23791d12e35466023e00d9","source":{"kind":"arxiv","id":"1905.07773","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.07773","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"arxiv_version","alias_value":"1905.07773v1","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07773","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"pith_short_12","alias_value":"IEKUQJ7RE6RJ","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"IEKUQJ7RE6RJHTMH","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"IEKUQJ7R","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:IEKUQJ7RE6RJHTMHHI5LUEYSED","target":"record","payload":{"canonical_record":{"source":{"id":"1905.07773","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-19T16:56:22Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"b9408c0196c076c0f0df845828c5c1e97399310f0a7ccc553a035f1d920ccd3c","abstract_canon_sha256":"fad5753896208086edafd3051e510f386c3e5e9932dbd008ecef16687d0f8ef6"},"schema_version":"1.0"},"canonical_sha256":"41154827f127a293cd873a3aba131220dbeea4457c23791d12e35466023e00d9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:48.538221Z","signature_b64":"HS17Vmer1lcF7743vgTmLqYkbDjvAv5xbH3Ag+tWyMaia7YDd16LhK1Ar/oxtucTqERoEXVaaJv/KJ2ojYpOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41154827f127a293cd873a3aba131220dbeea4457c23791d12e35466023e00d9","last_reissued_at":"2026-05-17T23:45:48.537689Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:48.537689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.07773","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":"2026-05-17T23:45:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kL+UpCC99BJSrVyYubtFDWppOS8FTXK843yxqoN24nmLS3fKCwzrqBPPA92Z4cz4DZUz9J4QWRm5KMobihCLDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T00:35:21.923486Z"},"content_sha256":"280bf4718e1e4ecd44a693a059d95dcd3cce36f94ee92cff887caf9f66b2ee4a","schema_version":"1.0","event_id":"sha256:280bf4718e1e4ecd44a693a059d95dcd3cce36f94ee92cff887caf9f66b2ee4a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:IEKUQJ7RE6RJHTMHHI5LUEYSED","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Online Convex Optimization in Adversarial 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":"Aviv Rosenberg, Yishay Mansour","submitted_at":"2019-05-19T16:56:22Z","abstract_excerpt":"We consider online learning in episodic loop-free Markov decision processes (MDPs), where the loss function can change arbitrarily between episodes, and the transition function is not known to the learner. We show $\\tilde{O}(L|X|\\sqrt{|A|T})$ regret bound, where $T$ is the number of episodes, $X$ is the state space, $A$ is the action space, and $L$ is the length of each episode. Our online algorithm is implemented using entropic regularization methodology, which allows to extend the original adversarial MDP model to handle convex performance criteria (different ways to aggregate the losses of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07773","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":"2026-05-17T23:45:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YglmrSKNQ2/ieK/saz2BkDVv9ol4EUmzV9ZXR81Hs+LgvSLazJIyqbz+Y5X5vbypI2Dr54PnaA97rXvaSaVBAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T00:35:21.924109Z"},"content_sha256":"1925f9b1e55dea021ab4e19c6a778e00dbfb598a1e7b77f7ba21aea48d81b761","schema_version":"1.0","event_id":"sha256:1925f9b1e55dea021ab4e19c6a778e00dbfb598a1e7b77f7ba21aea48d81b761"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IEKUQJ7RE6RJHTMHHI5LUEYSED/bundle.json","state_url":"https://pith.science/pith/IEKUQJ7RE6RJHTMHHI5LUEYSED/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IEKUQJ7RE6RJHTMHHI5LUEYSED/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":"2026-05-27T00:35:21Z","links":{"resolver":"https://pith.science/pith/IEKUQJ7RE6RJHTMHHI5LUEYSED","bundle":"https://pith.science/pith/IEKUQJ7RE6RJHTMHHI5LUEYSED/bundle.json","state":"https://pith.science/pith/IEKUQJ7RE6RJHTMHHI5LUEYSED/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IEKUQJ7RE6RJHTMHHI5LUEYSED/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:IEKUQJ7RE6RJHTMHHI5LUEYSED","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":"fad5753896208086edafd3051e510f386c3e5e9932dbd008ecef16687d0f8ef6","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-19T16:56:22Z","title_canon_sha256":"b9408c0196c076c0f0df845828c5c1e97399310f0a7ccc553a035f1d920ccd3c"},"schema_version":"1.0","source":{"id":"1905.07773","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.07773","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"arxiv_version","alias_value":"1905.07773v1","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07773","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"pith_short_12","alias_value":"IEKUQJ7RE6RJ","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"IEKUQJ7RE6RJHTMH","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"IEKUQJ7R","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:1925f9b1e55dea021ab4e19c6a778e00dbfb598a1e7b77f7ba21aea48d81b761","target":"graph","created_at":"2026-05-17T23:45:48Z","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 consider online learning in episodic loop-free Markov decision processes (MDPs), where the loss function can change arbitrarily between episodes, and the transition function is not known to the learner. We show $\\tilde{O}(L|X|\\sqrt{|A|T})$ regret bound, where $T$ is the number of episodes, $X$ is the state space, $A$ is the action space, and $L$ is the length of each episode. Our online algorithm is implemented using entropic regularization methodology, which allows to extend the original adversarial MDP model to handle convex performance criteria (different ways to aggregate the losses of ","authors_text":"Aviv Rosenberg, Yishay Mansour","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-19T16:56:22Z","title":"Online Convex Optimization in Adversarial Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07773","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":"sha256:280bf4718e1e4ecd44a693a059d95dcd3cce36f94ee92cff887caf9f66b2ee4a","target":"record","created_at":"2026-05-17T23:45:48Z","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":"fad5753896208086edafd3051e510f386c3e5e9932dbd008ecef16687d0f8ef6","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-19T16:56:22Z","title_canon_sha256":"b9408c0196c076c0f0df845828c5c1e97399310f0a7ccc553a035f1d920ccd3c"},"schema_version":"1.0","source":{"id":"1905.07773","kind":"arxiv","version":1}},"canonical_sha256":"41154827f127a293cd873a3aba131220dbeea4457c23791d12e35466023e00d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41154827f127a293cd873a3aba131220dbeea4457c23791d12e35466023e00d9","first_computed_at":"2026-05-17T23:45:48.537689Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:48.537689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HS17Vmer1lcF7743vgTmLqYkbDjvAv5xbH3Ag+tWyMaia7YDd16LhK1Ar/oxtucTqERoEXVaaJv/KJ2ojYpOBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:48.538221Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.07773","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:280bf4718e1e4ecd44a693a059d95dcd3cce36f94ee92cff887caf9f66b2ee4a","sha256:1925f9b1e55dea021ab4e19c6a778e00dbfb598a1e7b77f7ba21aea48d81b761"],"state_sha256":"f1e501a8d108efd242072a0732ef213598c57e859eff9639de80757731b0621f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0DUtbEmv5xd3Y/78E0NuUHNMw60HNcdHIprnJh8ExqcqMjhtHJmfin7zzkbPMGmiT/LAnBqRrY1FVQIROtw6Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T00:35:21.927705Z","bundle_sha256":"8b5ac1b4ec3f53cd0ba41eaf4c65a55251c06b1ee460b7e3a93d6a4211ff81df"}}