{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:3LIDLSMYJO5AFZSJH5VZP2EVMY","short_pith_number":"pith:3LIDLSMY","canonical_record":{"source":{"id":"1910.07072","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-15T22:01:31Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"bd73edd435016b964ae2325b24fdfc7562fd9e1ac5910a27ad494aa285422ace","abstract_canon_sha256":"3ac9342ca57842264d07a41e02a82e82e4c7bb980a1a5e731d567800e4807ffd"},"schema_version":"1.0"},"canonical_sha256":"dad035c9984bba02e6493f6b97e895662da4e2276245c979036c43df8631c6a4","source":{"kind":"arxiv","id":"1910.07072","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.07072","created_at":"2026-07-05T00:43:38Z"},{"alias_kind":"arxiv_version","alias_value":"1910.07072v2","created_at":"2026-07-05T00:43:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.07072","created_at":"2026-07-05T00:43:38Z"},{"alias_kind":"pith_short_12","alias_value":"3LIDLSMYJO5A","created_at":"2026-07-05T00:43:38Z"},{"alias_kind":"pith_short_16","alias_value":"3LIDLSMYJO5AFZSJ","created_at":"2026-07-05T00:43:38Z"},{"alias_kind":"pith_short_8","alias_value":"3LIDLSMY","created_at":"2026-07-05T00:43:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:3LIDLSMYJO5AFZSJH5VZP2EVMY","target":"record","payload":{"canonical_record":{"source":{"id":"1910.07072","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-15T22:01:31Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"bd73edd435016b964ae2325b24fdfc7562fd9e1ac5910a27ad494aa285422ace","abstract_canon_sha256":"3ac9342ca57842264d07a41e02a82e82e4c7bb980a1a5e731d567800e4807ffd"},"schema_version":"1.0"},"canonical_sha256":"dad035c9984bba02e6493f6b97e895662da4e2276245c979036c43df8631c6a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:43:38.649902Z","signature_b64":"BoArWbLlDKJiw+2io0i7hjhqQARipQOGK25TDZIGMpvfcys/7nt94TFb22k81fUTfMVGBxdQIPNT4JC8aMsjDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dad035c9984bba02e6493f6b97e895662da4e2276245c979036c43df8631c6a4","last_reissued_at":"2026-07-05T00:43:38.649408Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:43:38.649408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.07072","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":"2026-07-05T00:43:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1EHbJKoQ/COitLPgiX2OKDHNfQnASQcxU/o31cOygG9koBv1aLuPTAc/WRbQAMk/OqEI/iNednGc1OcFPWJ2Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T10:01:44.131167Z"},"content_sha256":"441803262197af3684c83479a90a2638b11cd8d7e5417e9bba8e89d6d8c6d229","schema_version":"1.0","event_id":"sha256:441803262197af3684c83479a90a2638b11cd8d7e5417e9bba8e89d6d8c6d229"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:3LIDLSMYJO5AFZSJH5VZP2EVMY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model-free Reinforcement Learning in Infinite-horizon Average-reward 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":"Chen-Yu Wei, Haipeng Luo, Hiteshi Sharma, Mehdi Jafarnia-Jahromi, Rahul Jain","submitted_at":"2019-10-15T22:01:31Z","abstract_excerpt":"Model-free reinforcement learning is known to be memory and computation efficient and more amendable to large scale problems. In this paper, two model-free algorithms are introduced for learning infinite-horizon average-reward Markov Decision Processes (MDPs). The first algorithm reduces the problem to the discounted-reward version and achieves $\\mathcal{O}(T^{2/3})$ regret after $T$ steps, under the minimal assumption of weakly communicating MDPs. To our knowledge, this is the first model-free algorithm for general MDPs in this setting. The second algorithm makes use of recent advances in ada"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.07072","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1910.07072/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T00:43:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AJjCeC7yebNI2BhmK897b0DXdqSI6XDSbBpkU4S7vT1cZ53vygOuW+I+R303+UKUftJ5pZS1C6Fr7a7KfitbAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T10:01:44.132783Z"},"content_sha256":"c9a287de553a31d7556f0c69a314ca9e75eddc197dc83dfbb81cce43519babad","schema_version":"1.0","event_id":"sha256:c9a287de553a31d7556f0c69a314ca9e75eddc197dc83dfbb81cce43519babad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3LIDLSMYJO5AFZSJH5VZP2EVMY/bundle.json","state_url":"https://pith.science/pith/3LIDLSMYJO5AFZSJH5VZP2EVMY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3LIDLSMYJO5AFZSJH5VZP2EVMY/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":"2026-08-13T10:01:44Z","links":{"resolver":"https://pith.science/pith/3LIDLSMYJO5AFZSJH5VZP2EVMY","bundle":"https://pith.science/pith/3LIDLSMYJO5AFZSJH5VZP2EVMY/bundle.json","state":"https://pith.science/pith/3LIDLSMYJO5AFZSJH5VZP2EVMY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3LIDLSMYJO5AFZSJH5VZP2EVMY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:3LIDLSMYJO5AFZSJH5VZP2EVMY","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":"3ac9342ca57842264d07a41e02a82e82e4c7bb980a1a5e731d567800e4807ffd","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-15T22:01:31Z","title_canon_sha256":"bd73edd435016b964ae2325b24fdfc7562fd9e1ac5910a27ad494aa285422ace"},"schema_version":"1.0","source":{"id":"1910.07072","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.07072","created_at":"2026-07-05T00:43:38Z"},{"alias_kind":"arxiv_version","alias_value":"1910.07072v2","created_at":"2026-07-05T00:43:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.07072","created_at":"2026-07-05T00:43:38Z"},{"alias_kind":"pith_short_12","alias_value":"3LIDLSMYJO5A","created_at":"2026-07-05T00:43:38Z"},{"alias_kind":"pith_short_16","alias_value":"3LIDLSMYJO5AFZSJ","created_at":"2026-07-05T00:43:38Z"},{"alias_kind":"pith_short_8","alias_value":"3LIDLSMY","created_at":"2026-07-05T00:43:38Z"}],"graph_snapshots":[{"event_id":"sha256:c9a287de553a31d7556f0c69a314ca9e75eddc197dc83dfbb81cce43519babad","target":"graph","created_at":"2026-07-05T00:43:38Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1910.07072/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-free reinforcement learning is known to be memory and computation efficient and more amendable to large scale problems. In this paper, two model-free algorithms are introduced for learning infinite-horizon average-reward Markov Decision Processes (MDPs). The first algorithm reduces the problem to the discounted-reward version and achieves $\\mathcal{O}(T^{2/3})$ regret after $T$ steps, under the minimal assumption of weakly communicating MDPs. To our knowledge, this is the first model-free algorithm for general MDPs in this setting. The second algorithm makes use of recent advances in ada","authors_text":"Chen-Yu Wei, Haipeng Luo, Hiteshi Sharma, Mehdi Jafarnia-Jahromi, Rahul Jain","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-15T22:01:31Z","title":"Model-free Reinforcement Learning in Infinite-horizon Average-reward Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.07072","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":"sha256:441803262197af3684c83479a90a2638b11cd8d7e5417e9bba8e89d6d8c6d229","target":"record","created_at":"2026-07-05T00:43:38Z","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":"3ac9342ca57842264d07a41e02a82e82e4c7bb980a1a5e731d567800e4807ffd","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-15T22:01:31Z","title_canon_sha256":"bd73edd435016b964ae2325b24fdfc7562fd9e1ac5910a27ad494aa285422ace"},"schema_version":"1.0","source":{"id":"1910.07072","kind":"arxiv","version":2}},"canonical_sha256":"dad035c9984bba02e6493f6b97e895662da4e2276245c979036c43df8631c6a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dad035c9984bba02e6493f6b97e895662da4e2276245c979036c43df8631c6a4","first_computed_at":"2026-07-05T00:43:38.649408Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:43:38.649408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BoArWbLlDKJiw+2io0i7hjhqQARipQOGK25TDZIGMpvfcys/7nt94TFb22k81fUTfMVGBxdQIPNT4JC8aMsjDg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:43:38.649902Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.07072","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:441803262197af3684c83479a90a2638b11cd8d7e5417e9bba8e89d6d8c6d229","sha256:c9a287de553a31d7556f0c69a314ca9e75eddc197dc83dfbb81cce43519babad"],"state_sha256":"cb9bcaa24015042f075937aeb9b84b3bd57f2352cf2d47691ee2119b76b4d02d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ovLEuPpcPLB/9NR0zGnabTDmYBxlC4zoQfJGypdRx6Gy3FyUL5pIlMeB+YRGUKyUp7J+iMNoRJ3adrvgBlr5BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T10:01:44.225796Z","bundle_sha256":"8f3020b387fdde18788ad0ed31645e1e90063584be9e01810d8a016fdd537592"}}