{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:TONIGPGFDTGAGLT3OJUF4QBQVD","short_pith_number":"pith:TONIGPGF","canonical_record":{"source":{"id":"1605.08062","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-25T20:15:38Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"12b45cd54ce4d70f65b2f10fcef7d223d386bcd9c4189bc009e23a82d8e5202d","abstract_canon_sha256":"132dc922df10212fcac659d7cdc164ae2c100a3a7a5c445746f65043601b627c"},"schema_version":"1.0"},"canonical_sha256":"9b9a833cc51ccc032e7b72685e4030a8e5db2f204ff8549cea04deb7d4c0f807","source":{"kind":"arxiv","id":"1605.08062","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.08062","created_at":"2026-05-18T01:13:09Z"},{"alias_kind":"arxiv_version","alias_value":"1605.08062v2","created_at":"2026-05-18T01:13:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.08062","created_at":"2026-05-18T01:13:09Z"},{"alias_kind":"pith_short_12","alias_value":"TONIGPGFDTGA","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"TONIGPGFDTGAGLT3","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"TONIGPGF","created_at":"2026-05-18T12:30:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:TONIGPGFDTGAGLT3OJUF4QBQVD","target":"record","payload":{"canonical_record":{"source":{"id":"1605.08062","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-25T20:15:38Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"12b45cd54ce4d70f65b2f10fcef7d223d386bcd9c4189bc009e23a82d8e5202d","abstract_canon_sha256":"132dc922df10212fcac659d7cdc164ae2c100a3a7a5c445746f65043601b627c"},"schema_version":"1.0"},"canonical_sha256":"9b9a833cc51ccc032e7b72685e4030a8e5db2f204ff8549cea04deb7d4c0f807","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:09.264170Z","signature_b64":"ysmjDgoK9sKc243o1g3j/caRdTytYwYbsQWxo86U/rcvZvVVqCntBMOf3uyvZKZ8yZM0eEuGgQBDuRKZyzAKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b9a833cc51ccc032e7b72685e4030a8e5db2f204ff8549cea04deb7d4c0f807","last_reissued_at":"2026-05-18T01:13:09.263834Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:09.263834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1605.08062","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":"2026-05-18T01:13:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PBikH3Z2GmtDlA9Apwf3asz0e9JqgBr78G9pdHT4Pfty8+HBInKonBbgRv9bqEiXxhvPFmjqOFOIKpTnX+kBBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T23:06:24.365864Z"},"content_sha256":"bbd3ac0c71c204a86afe829a0546e37e5a513aa2f475cc48715ecd837de0b957","schema_version":"1.0","event_id":"sha256:bbd3ac0c71c204a86afe829a0546e37e5a513aa2f475cc48715ecd837de0b957"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:TONIGPGFDTGAGLT3OJUF4QBQVD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A PAC RL Algorithm for Episodic POMDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Emma Brunskill, Shayan Doroudi, Zhaohan Daniel Guo","submitted_at":"2016-05-25T20:15:38Z","abstract_excerpt":"Many interesting real world domains involve reinforcement learning (RL) in partially observable environments. Efficient learning in such domains is important, but existing sample complexity bounds for partially observable RL are at least exponential in the episode length. We give, to our knowledge, the first partially observable RL algorithm with a polynomial bound on the number of episodes on which the algorithm may not achieve near-optimal performance. Our algorithm is suitable for an important class of episodic POMDPs. Our approach builds on recent advances in method of moments for latent v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.08062","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":"2026-05-18T01:13:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DHb/GwLleFxOrEJGoagksN7vsiAw0itIKr5YnBVAPEaDqUbhfik9qsFI6u60UQmY7h1Gc28apRinLsRW4qmZDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T23:06:24.366562Z"},"content_sha256":"abd2bb456e2371d53e808a58285a3f9ddb0d9a830eca8afb5de635e39c0bbe31","schema_version":"1.0","event_id":"sha256:abd2bb456e2371d53e808a58285a3f9ddb0d9a830eca8afb5de635e39c0bbe31"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TONIGPGFDTGAGLT3OJUF4QBQVD/bundle.json","state_url":"https://pith.science/pith/TONIGPGFDTGAGLT3OJUF4QBQVD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TONIGPGFDTGAGLT3OJUF4QBQVD/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":"2026-06-10T23:06:24Z","links":{"resolver":"https://pith.science/pith/TONIGPGFDTGAGLT3OJUF4QBQVD","bundle":"https://pith.science/pith/TONIGPGFDTGAGLT3OJUF4QBQVD/bundle.json","state":"https://pith.science/pith/TONIGPGFDTGAGLT3OJUF4QBQVD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TONIGPGFDTGAGLT3OJUF4QBQVD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:TONIGPGFDTGAGLT3OJUF4QBQVD","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":"132dc922df10212fcac659d7cdc164ae2c100a3a7a5c445746f65043601b627c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-25T20:15:38Z","title_canon_sha256":"12b45cd54ce4d70f65b2f10fcef7d223d386bcd9c4189bc009e23a82d8e5202d"},"schema_version":"1.0","source":{"id":"1605.08062","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.08062","created_at":"2026-05-18T01:13:09Z"},{"alias_kind":"arxiv_version","alias_value":"1605.08062v2","created_at":"2026-05-18T01:13:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.08062","created_at":"2026-05-18T01:13:09Z"},{"alias_kind":"pith_short_12","alias_value":"TONIGPGFDTGA","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"TONIGPGFDTGAGLT3","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"TONIGPGF","created_at":"2026-05-18T12:30:46Z"}],"graph_snapshots":[{"event_id":"sha256:abd2bb456e2371d53e808a58285a3f9ddb0d9a830eca8afb5de635e39c0bbe31","target":"graph","created_at":"2026-05-18T01:13:09Z","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":"Many interesting real world domains involve reinforcement learning (RL) in partially observable environments. Efficient learning in such domains is important, but existing sample complexity bounds for partially observable RL are at least exponential in the episode length. We give, to our knowledge, the first partially observable RL algorithm with a polynomial bound on the number of episodes on which the algorithm may not achieve near-optimal performance. Our algorithm is suitable for an important class of episodic POMDPs. Our approach builds on recent advances in method of moments for latent v","authors_text":"Emma Brunskill, Shayan Doroudi, Zhaohan Daniel Guo","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-25T20:15:38Z","title":"A PAC RL Algorithm for Episodic POMDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.08062","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:bbd3ac0c71c204a86afe829a0546e37e5a513aa2f475cc48715ecd837de0b957","target":"record","created_at":"2026-05-18T01:13:09Z","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":"132dc922df10212fcac659d7cdc164ae2c100a3a7a5c445746f65043601b627c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-25T20:15:38Z","title_canon_sha256":"12b45cd54ce4d70f65b2f10fcef7d223d386bcd9c4189bc009e23a82d8e5202d"},"schema_version":"1.0","source":{"id":"1605.08062","kind":"arxiv","version":2}},"canonical_sha256":"9b9a833cc51ccc032e7b72685e4030a8e5db2f204ff8549cea04deb7d4c0f807","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b9a833cc51ccc032e7b72685e4030a8e5db2f204ff8549cea04deb7d4c0f807","first_computed_at":"2026-05-18T01:13:09.263834Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:13:09.263834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ysmjDgoK9sKc243o1g3j/caRdTytYwYbsQWxo86U/rcvZvVVqCntBMOf3uyvZKZ8yZM0eEuGgQBDuRKZyzAKBg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:13:09.264170Z","signed_message":"canonical_sha256_bytes"},"source_id":"1605.08062","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bbd3ac0c71c204a86afe829a0546e37e5a513aa2f475cc48715ecd837de0b957","sha256:abd2bb456e2371d53e808a58285a3f9ddb0d9a830eca8afb5de635e39c0bbe31"],"state_sha256":"dd1d04ead2b8be06a2e5412635489c1dceda1308976c8e22d123b8bc9cd649b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dX8D5k4R2jxhqjKEHam/q5BQ3JjYK8VhdkFmbUtVahl/OMlcocHNJG57cyW7rjfzI3gbrTGYR6Jok4tXcLh+DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T23:06:24.370242Z","bundle_sha256":"86c97f8bd562702e515c162478f653f75782f647698149861a18d838beed11c9"}}