{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:FVUPQBQHN4G5SSHWAGQDVG7BDX","short_pith_number":"pith:FVUPQBQH","canonical_record":{"source":{"id":"2106.11612","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-22T08:48:56Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"ac5a50bd4c8c4be2583392cd65f7d9b625be80bcb780934db497e62d99fc3c8c","abstract_canon_sha256":"a3d7d346e6c78dddc43c1b047fd886b20a3ebcf57eab59779ec1cb2e427af82f"},"schema_version":"1.0"},"canonical_sha256":"2d68f806076f0dd948f601a03a9be11de365c218d895e8518bfe69bee7713caa","source":{"kind":"arxiv","id":"2106.11612","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.11612","created_at":"2026-07-05T03:44:45Z"},{"alias_kind":"arxiv_version","alias_value":"2106.11612v2","created_at":"2026-07-05T03:44:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.11612","created_at":"2026-07-05T03:44:45Z"},{"alias_kind":"pith_short_12","alias_value":"FVUPQBQHN4G5","created_at":"2026-07-05T03:44:45Z"},{"alias_kind":"pith_short_16","alias_value":"FVUPQBQHN4G5SSHW","created_at":"2026-07-05T03:44:45Z"},{"alias_kind":"pith_short_8","alias_value":"FVUPQBQH","created_at":"2026-07-05T03:44:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:FVUPQBQHN4G5SSHWAGQDVG7BDX","target":"record","payload":{"canonical_record":{"source":{"id":"2106.11612","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-22T08:48:56Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"ac5a50bd4c8c4be2583392cd65f7d9b625be80bcb780934db497e62d99fc3c8c","abstract_canon_sha256":"a3d7d346e6c78dddc43c1b047fd886b20a3ebcf57eab59779ec1cb2e427af82f"},"schema_version":"1.0"},"canonical_sha256":"2d68f806076f0dd948f601a03a9be11de365c218d895e8518bfe69bee7713caa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:44:45.007414Z","signature_b64":"/2FxANgdeLKwhhBFuRRnObWqui4B98Xu0LjwRHR6tz2qxrcuhRvPcygDSL+OIZdFKjFeGC2nYaiUH3N5QivJAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d68f806076f0dd948f601a03a9be11de365c218d895e8518bfe69bee7713caa","last_reissued_at":"2026-07-05T03:44:45.006910Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:44:45.006910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.11612","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":"2026-07-05T03:44:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KuamTy3AmtTugLJPiHWiqmI0QgHkHQTd9q4yiwfxl84w2B4+LrsduGjkY2FSskLPGuMm9hG0uC9VNVZmsA68Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:46:02.098373Z"},"content_sha256":"f0d77a50730035a5d0b83bc0e01357d463407f94e7f7dce07818530ed21318cd","schema_version":"1.0","event_id":"sha256:f0d77a50730035a5d0b83bc0e01357d463407f94e7f7dce07818530ed21318cd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:FVUPQBQHN4G5SSHWAGQDVG7BDX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Uniform-PAC Bounds for Reinforcement Learning with Linear Function Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongruo Zhou, Jiafan He, Quanquan Gu","submitted_at":"2021-06-22T08:48:56Z","abstract_excerpt":"We study reinforcement learning (RL) with linear function approximation. Existing algorithms for this problem only have high-probability regret and/or Probably Approximately Correct (PAC) sample complexity guarantees, which cannot guarantee the convergence to the optimal policy. In this paper, in order to overcome the limitation of existing algorithms, we propose a new algorithm called FLUTE, which enjoys uniform-PAC convergence to the optimal policy with high probability. The uniform-PAC guarantee is the strongest possible guarantee for reinforcement learning in the literature, which can dire"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.11612","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/2106.11612/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":"2026-07-05T03:44:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kaBBWaikiyuAlaJgcF3q9urbeUcK17r2YiuklUv4/25tBuupV/Ie2TSYkVfVBq2QrxfRVcge9Wmg+29nHgocAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:46:02.098755Z"},"content_sha256":"600d5c5870b81253159ea31f5696654f2ee217ed3e8706b8ed4453f3ceaed173","schema_version":"1.0","event_id":"sha256:600d5c5870b81253159ea31f5696654f2ee217ed3e8706b8ed4453f3ceaed173"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FVUPQBQHN4G5SSHWAGQDVG7BDX/bundle.json","state_url":"https://pith.science/pith/FVUPQBQHN4G5SSHWAGQDVG7BDX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FVUPQBQHN4G5SSHWAGQDVG7BDX/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":"2026-07-06T08:46:02Z","links":{"resolver":"https://pith.science/pith/FVUPQBQHN4G5SSHWAGQDVG7BDX","bundle":"https://pith.science/pith/FVUPQBQHN4G5SSHWAGQDVG7BDX/bundle.json","state":"https://pith.science/pith/FVUPQBQHN4G5SSHWAGQDVG7BDX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FVUPQBQHN4G5SSHWAGQDVG7BDX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FVUPQBQHN4G5SSHWAGQDVG7BDX","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":"a3d7d346e6c78dddc43c1b047fd886b20a3ebcf57eab59779ec1cb2e427af82f","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-22T08:48:56Z","title_canon_sha256":"ac5a50bd4c8c4be2583392cd65f7d9b625be80bcb780934db497e62d99fc3c8c"},"schema_version":"1.0","source":{"id":"2106.11612","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.11612","created_at":"2026-07-05T03:44:45Z"},{"alias_kind":"arxiv_version","alias_value":"2106.11612v2","created_at":"2026-07-05T03:44:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.11612","created_at":"2026-07-05T03:44:45Z"},{"alias_kind":"pith_short_12","alias_value":"FVUPQBQHN4G5","created_at":"2026-07-05T03:44:45Z"},{"alias_kind":"pith_short_16","alias_value":"FVUPQBQHN4G5SSHW","created_at":"2026-07-05T03:44:45Z"},{"alias_kind":"pith_short_8","alias_value":"FVUPQBQH","created_at":"2026-07-05T03:44:45Z"}],"graph_snapshots":[{"event_id":"sha256:600d5c5870b81253159ea31f5696654f2ee217ed3e8706b8ed4453f3ceaed173","target":"graph","created_at":"2026-07-05T03:44:45Z","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/2106.11612/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study reinforcement learning (RL) with linear function approximation. Existing algorithms for this problem only have high-probability regret and/or Probably Approximately Correct (PAC) sample complexity guarantees, which cannot guarantee the convergence to the optimal policy. In this paper, in order to overcome the limitation of existing algorithms, we propose a new algorithm called FLUTE, which enjoys uniform-PAC convergence to the optimal policy with high probability. The uniform-PAC guarantee is the strongest possible guarantee for reinforcement learning in the literature, which can dire","authors_text":"Dongruo Zhou, Jiafan He, Quanquan Gu","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-22T08:48:56Z","title":"Uniform-PAC Bounds for Reinforcement Learning with Linear Function Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.11612","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:f0d77a50730035a5d0b83bc0e01357d463407f94e7f7dce07818530ed21318cd","target":"record","created_at":"2026-07-05T03:44:45Z","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":"a3d7d346e6c78dddc43c1b047fd886b20a3ebcf57eab59779ec1cb2e427af82f","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-22T08:48:56Z","title_canon_sha256":"ac5a50bd4c8c4be2583392cd65f7d9b625be80bcb780934db497e62d99fc3c8c"},"schema_version":"1.0","source":{"id":"2106.11612","kind":"arxiv","version":2}},"canonical_sha256":"2d68f806076f0dd948f601a03a9be11de365c218d895e8518bfe69bee7713caa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d68f806076f0dd948f601a03a9be11de365c218d895e8518bfe69bee7713caa","first_computed_at":"2026-07-05T03:44:45.006910Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:44:45.006910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/2FxANgdeLKwhhBFuRRnObWqui4B98Xu0LjwRHR6tz2qxrcuhRvPcygDSL+OIZdFKjFeGC2nYaiUH3N5QivJAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:44:45.007414Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.11612","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0d77a50730035a5d0b83bc0e01357d463407f94e7f7dce07818530ed21318cd","sha256:600d5c5870b81253159ea31f5696654f2ee217ed3e8706b8ed4453f3ceaed173"],"state_sha256":"941d2a9150c9bcaece7df3884ebce151132fe7e26a1eb35f12000016d306f34f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9a/HCWwegvIUDFuBwARBpYrqGDFsAMbj4JZWCa9JKXRc7C7AcTHzea89r/jcUgL1S7OsElzxOMxa5ogP5u6uAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T08:46:02.100837Z","bundle_sha256":"4d0b804131263823caaeed2f6149e9eada3dac30da789fc7182801d187c05ba0"}}