{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WOXRXRHM26VVYK2WFL4O3EIMYX","short_pith_number":"pith:WOXRXRHM","canonical_record":{"source":{"id":"2310.06113","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T19:40:54Z","cross_cats_sorted":["cs.AI","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"e5ac92bf6d907284edcccf3d2deef35979bb627e744804b47d25e2ef8afdd48a","abstract_canon_sha256":"a34056d7b8c582f14468947514c80c809a7841fc41d5dca2e51c33e6a957a8c0"},"schema_version":"1.0"},"canonical_sha256":"b3af1bc4ecd7ab5c2b562af8ed910cc5ca53b2bcdc37b3066c36a462c49ff326","source":{"kind":"arxiv","id":"2310.06113","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.06113","created_at":"2026-07-05T06:59:05Z"},{"alias_kind":"arxiv_version","alias_value":"2310.06113v1","created_at":"2026-07-05T06:59:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06113","created_at":"2026-07-05T06:59:05Z"},{"alias_kind":"pith_short_12","alias_value":"WOXRXRHM26VV","created_at":"2026-07-05T06:59:05Z"},{"alias_kind":"pith_short_16","alias_value":"WOXRXRHM26VVYK2W","created_at":"2026-07-05T06:59:05Z"},{"alias_kind":"pith_short_8","alias_value":"WOXRXRHM","created_at":"2026-07-05T06:59:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WOXRXRHM26VVYK2WFL4O3EIMYX","target":"record","payload":{"canonical_record":{"source":{"id":"2310.06113","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T19:40:54Z","cross_cats_sorted":["cs.AI","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"e5ac92bf6d907284edcccf3d2deef35979bb627e744804b47d25e2ef8afdd48a","abstract_canon_sha256":"a34056d7b8c582f14468947514c80c809a7841fc41d5dca2e51c33e6a957a8c0"},"schema_version":"1.0"},"canonical_sha256":"b3af1bc4ecd7ab5c2b562af8ed910cc5ca53b2bcdc37b3066c36a462c49ff326","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:05.835732Z","signature_b64":"XeuZ1H0SdKils70f5gfIz+2GbZ5Ok3CZkWtcXBLz/L0Sb4OBt1S8mhpe/WP+lhq/hyZUwGPD389s/q78qzicDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3af1bc4ecd7ab5c2b562af8ed910cc5ca53b2bcdc37b3066c36a462c49ff326","last_reissued_at":"2026-07-05T06:59:05.835345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:05.835345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.06113","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":"2026-07-05T06:59:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wFlCmftSR3lYy/Jefe5T/XU4ELI8hauDjV9zJsezcAAharxrPtLJMF/skA7G5JfKk9zyaRPD/4sjQtIf0J3rCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T06:07:12.431199Z"},"content_sha256":"8913a979ae652ab7ba1ebb600ed684ccfd302fa6dab0bc54e0af953f4958be01","schema_version":"1.0","event_id":"sha256:8913a979ae652ab7ba1ebb600ed684ccfd302fa6dab0bc54e0af953f4958be01"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WOXRXRHM26VVYK2WFL4O3EIMYX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When is Agnostic Reinforcement Learning Statistically Tractable?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Alexander Rakhlin, Ayush Sekhari, Gene Li, Nathan Srebro, Zeyu Jia","submitted_at":"2023-10-09T19:40:54Z","abstract_excerpt":"We study the problem of agnostic PAC reinforcement learning (RL): given a policy class $\\Pi$, how many rounds of interaction with an unknown MDP (with a potentially large state and action space) are required to learn an $\\epsilon$-suboptimal policy with respect to $\\Pi$? Towards that end, we introduce a new complexity measure, called the \\emph{spanning capacity}, that depends solely on the set $\\Pi$ and is independent of the MDP dynamics. With a generative model, we show that for any policy class $\\Pi$, bounded spanning capacity characterizes PAC learnability. However, for online RL, the situa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06113","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.06113/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":"2026-07-05T06:59:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7WAlPggNJT0l02wGWuh2V6Q35oDJ1EA6d/k1j/Wf43RSY96gJ1HP8UAV9aVWLl3hNrzcwKCr0wWTzLZ7PIVKDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T06:07:12.432071Z"},"content_sha256":"846c18ba9751bc9e21a603d6b4a9cc857d208b800034770f70964cc23794c473","schema_version":"1.0","event_id":"sha256:846c18ba9751bc9e21a603d6b4a9cc857d208b800034770f70964cc23794c473"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WOXRXRHM26VVYK2WFL4O3EIMYX/bundle.json","state_url":"https://pith.science/pith/WOXRXRHM26VVYK2WFL4O3EIMYX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WOXRXRHM26VVYK2WFL4O3EIMYX/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":"2026-08-23T06:07:12Z","links":{"resolver":"https://pith.science/pith/WOXRXRHM26VVYK2WFL4O3EIMYX","bundle":"https://pith.science/pith/WOXRXRHM26VVYK2WFL4O3EIMYX/bundle.json","state":"https://pith.science/pith/WOXRXRHM26VVYK2WFL4O3EIMYX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WOXRXRHM26VVYK2WFL4O3EIMYX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WOXRXRHM26VVYK2WFL4O3EIMYX","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":"a34056d7b8c582f14468947514c80c809a7841fc41d5dca2e51c33e6a957a8c0","cross_cats_sorted":["cs.AI","math.ST","stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T19:40:54Z","title_canon_sha256":"e5ac92bf6d907284edcccf3d2deef35979bb627e744804b47d25e2ef8afdd48a"},"schema_version":"1.0","source":{"id":"2310.06113","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.06113","created_at":"2026-07-05T06:59:05Z"},{"alias_kind":"arxiv_version","alias_value":"2310.06113v1","created_at":"2026-07-05T06:59:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06113","created_at":"2026-07-05T06:59:05Z"},{"alias_kind":"pith_short_12","alias_value":"WOXRXRHM26VV","created_at":"2026-07-05T06:59:05Z"},{"alias_kind":"pith_short_16","alias_value":"WOXRXRHM26VVYK2W","created_at":"2026-07-05T06:59:05Z"},{"alias_kind":"pith_short_8","alias_value":"WOXRXRHM","created_at":"2026-07-05T06:59:05Z"}],"graph_snapshots":[{"event_id":"sha256:846c18ba9751bc9e21a603d6b4a9cc857d208b800034770f70964cc23794c473","target":"graph","created_at":"2026-07-05T06:59:05Z","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/2310.06113/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of agnostic PAC reinforcement learning (RL): given a policy class $\\Pi$, how many rounds of interaction with an unknown MDP (with a potentially large state and action space) are required to learn an $\\epsilon$-suboptimal policy with respect to $\\Pi$? Towards that end, we introduce a new complexity measure, called the \\emph{spanning capacity}, that depends solely on the set $\\Pi$ and is independent of the MDP dynamics. With a generative model, we show that for any policy class $\\Pi$, bounded spanning capacity characterizes PAC learnability. However, for online RL, the situa","authors_text":"Alexander Rakhlin, Ayush Sekhari, Gene Li, Nathan Srebro, Zeyu Jia","cross_cats":["cs.AI","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T19:40:54Z","title":"When is Agnostic Reinforcement Learning Statistically Tractable?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06113","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":"sha256:8913a979ae652ab7ba1ebb600ed684ccfd302fa6dab0bc54e0af953f4958be01","target":"record","created_at":"2026-07-05T06:59:05Z","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":"a34056d7b8c582f14468947514c80c809a7841fc41d5dca2e51c33e6a957a8c0","cross_cats_sorted":["cs.AI","math.ST","stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T19:40:54Z","title_canon_sha256":"e5ac92bf6d907284edcccf3d2deef35979bb627e744804b47d25e2ef8afdd48a"},"schema_version":"1.0","source":{"id":"2310.06113","kind":"arxiv","version":1}},"canonical_sha256":"b3af1bc4ecd7ab5c2b562af8ed910cc5ca53b2bcdc37b3066c36a462c49ff326","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b3af1bc4ecd7ab5c2b562af8ed910cc5ca53b2bcdc37b3066c36a462c49ff326","first_computed_at":"2026-07-05T06:59:05.835345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:59:05.835345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XeuZ1H0SdKils70f5gfIz+2GbZ5Ok3CZkWtcXBLz/L0Sb4OBt1S8mhpe/WP+lhq/hyZUwGPD389s/q78qzicDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:59:05.835732Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.06113","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8913a979ae652ab7ba1ebb600ed684ccfd302fa6dab0bc54e0af953f4958be01","sha256:846c18ba9751bc9e21a603d6b4a9cc857d208b800034770f70964cc23794c473"],"state_sha256":"02cce80674f699c53b3a9384530787d4e97756c2859c54484c55ead8a669eff8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i1lFhDX7xpyE53/HP37a8Rh9TIgZc90tKSytxn33KCR5NU9E59Yhwv2WBNLAZfSg15yiAXuF6LW+MUArGBVkAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T06:07:12.437950Z","bundle_sha256":"e0e1e1131dadd2470724b54a771721b8a5bcad4d03d7b47d0ec8faaec6746780"}}