{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:RXYOBC6DR7HVWWK5TH5ZW6CTZJ","short_pith_number":"pith:RXYOBC6D","canonical_record":{"source":{"id":"1910.08412","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-18T13:33:17Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"36f5b1af32264b7c45fabc29c95461c4b0ca3a8a57c6005bd36ab4fec02661cb","abstract_canon_sha256":"8fc9d800c557577babc84602d12c390222793e55faf29ff43f047cd01b345f02"},"schema_version":"1.0"},"canonical_sha256":"8df0e08bc38fcf5b595d99fb9b7853ca70d4627d5db9cb7e2e010ad6cb97881e","source":{"kind":"arxiv","id":"1910.08412","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.08412","created_at":"2026-07-05T05:36:28Z"},{"alias_kind":"arxiv_version","alias_value":"1910.08412v3","created_at":"2026-07-05T05:36:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.08412","created_at":"2026-07-05T05:36:28Z"},{"alias_kind":"pith_short_12","alias_value":"RXYOBC6DR7HV","created_at":"2026-07-05T05:36:28Z"},{"alias_kind":"pith_short_16","alias_value":"RXYOBC6DR7HVWWK5","created_at":"2026-07-05T05:36:28Z"},{"alias_kind":"pith_short_8","alias_value":"RXYOBC6D","created_at":"2026-07-05T05:36:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:RXYOBC6DR7HVWWK5TH5ZW6CTZJ","target":"record","payload":{"canonical_record":{"source":{"id":"1910.08412","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-18T13:33:17Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"36f5b1af32264b7c45fabc29c95461c4b0ca3a8a57c6005bd36ab4fec02661cb","abstract_canon_sha256":"8fc9d800c557577babc84602d12c390222793e55faf29ff43f047cd01b345f02"},"schema_version":"1.0"},"canonical_sha256":"8df0e08bc38fcf5b595d99fb9b7853ca70d4627d5db9cb7e2e010ad6cb97881e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:28.210010Z","signature_b64":"pOJzElZim0X1olcY27j3MMp+DOKJnyZY7LXw5enmuL6MskKzcPuzHmb/UTQDokuGj63Dyl3Ohbi0Z6h97iIEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8df0e08bc38fcf5b595d99fb9b7853ca70d4627d5db9cb7e2e010ad6cb97881e","last_reissued_at":"2026-07-05T05:36:28.209529Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:28.209529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.08412","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:36:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3rmsUqIb9r0yi/PmUBh0iJPiRegwE1/HWbm870VMzUdDv8k+ImWtzNlQfNC0jDqIXxPfSy7V5DAbyOrHj2QtAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:56:48.817818Z"},"content_sha256":"b460d2a5a358885474eb5ffb0680a4b0d2ca0676556809b51e64b21cb038de07","schema_version":"1.0","event_id":"sha256:b460d2a5a358885474eb5ffb0680a4b0d2ca0676556809b51e64b21cb038de07"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:RXYOBC6DR7HVWWK5TH5ZW6CTZJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Sample Complexity of Actor-Critic Method for Reinforcement Learning with Function Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alec Koppel, Alejandro Ribeiro, Harshat Kumar","submitted_at":"2019-10-18T13:33:17Z","abstract_excerpt":"Reinforcement learning, mathematically described by Markov Decision Problems, may be approached either through dynamic programming or policy search. Actor-critic algorithms combine the merits of both approaches by alternating between steps to estimate the value function and policy gradient updates. Due to the fact that the updates exhibit correlated noise and biased gradient updates, only the asymptotic behavior of actor-critic is known by connecting its behavior to dynamical systems. This work puts forth a new variant of actor-critic that employs Monte Carlo rollouts during the policy search "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.08412","kind":"arxiv","version":3},"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/1910.08412/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":"2026-07-05T05:36:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hoQJ9WLpCSQ6RoXCWblhm+Ua1UXX55kVRyfNCfUkszS+6Ee+Im6mDgiD4i2UquFtPqQklbdMnJCHzIvZAn86Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:56:48.818334Z"},"content_sha256":"b183e7ce826711d022d71e1d748fe7261dc399aec9c976df09b17a6d01aa537a","schema_version":"1.0","event_id":"sha256:b183e7ce826711d022d71e1d748fe7261dc399aec9c976df09b17a6d01aa537a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RXYOBC6DR7HVWWK5TH5ZW6CTZJ/bundle.json","state_url":"https://pith.science/pith/RXYOBC6DR7HVWWK5TH5ZW6CTZJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RXYOBC6DR7HVWWK5TH5ZW6CTZJ/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":"2026-08-03T21:56:48Z","links":{"resolver":"https://pith.science/pith/RXYOBC6DR7HVWWK5TH5ZW6CTZJ","bundle":"https://pith.science/pith/RXYOBC6DR7HVWWK5TH5ZW6CTZJ/bundle.json","state":"https://pith.science/pith/RXYOBC6DR7HVWWK5TH5ZW6CTZJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RXYOBC6DR7HVWWK5TH5ZW6CTZJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:RXYOBC6DR7HVWWK5TH5ZW6CTZJ","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":"8fc9d800c557577babc84602d12c390222793e55faf29ff43f047cd01b345f02","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-18T13:33:17Z","title_canon_sha256":"36f5b1af32264b7c45fabc29c95461c4b0ca3a8a57c6005bd36ab4fec02661cb"},"schema_version":"1.0","source":{"id":"1910.08412","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.08412","created_at":"2026-07-05T05:36:28Z"},{"alias_kind":"arxiv_version","alias_value":"1910.08412v3","created_at":"2026-07-05T05:36:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.08412","created_at":"2026-07-05T05:36:28Z"},{"alias_kind":"pith_short_12","alias_value":"RXYOBC6DR7HV","created_at":"2026-07-05T05:36:28Z"},{"alias_kind":"pith_short_16","alias_value":"RXYOBC6DR7HVWWK5","created_at":"2026-07-05T05:36:28Z"},{"alias_kind":"pith_short_8","alias_value":"RXYOBC6D","created_at":"2026-07-05T05:36:28Z"}],"graph_snapshots":[{"event_id":"sha256:b183e7ce826711d022d71e1d748fe7261dc399aec9c976df09b17a6d01aa537a","target":"graph","created_at":"2026-07-05T05:36:28Z","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/1910.08412/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning, mathematically described by Markov Decision Problems, may be approached either through dynamic programming or policy search. Actor-critic algorithms combine the merits of both approaches by alternating between steps to estimate the value function and policy gradient updates. Due to the fact that the updates exhibit correlated noise and biased gradient updates, only the asymptotic behavior of actor-critic is known by connecting its behavior to dynamical systems. This work puts forth a new variant of actor-critic that employs Monte Carlo rollouts during the policy search ","authors_text":"Alec Koppel, Alejandro Ribeiro, Harshat Kumar","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-18T13:33:17Z","title":"On the Sample Complexity of Actor-Critic Method for Reinforcement Learning with Function Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.08412","kind":"arxiv","version":3},"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:b460d2a5a358885474eb5ffb0680a4b0d2ca0676556809b51e64b21cb038de07","target":"record","created_at":"2026-07-05T05:36:28Z","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":"8fc9d800c557577babc84602d12c390222793e55faf29ff43f047cd01b345f02","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-18T13:33:17Z","title_canon_sha256":"36f5b1af32264b7c45fabc29c95461c4b0ca3a8a57c6005bd36ab4fec02661cb"},"schema_version":"1.0","source":{"id":"1910.08412","kind":"arxiv","version":3}},"canonical_sha256":"8df0e08bc38fcf5b595d99fb9b7853ca70d4627d5db9cb7e2e010ad6cb97881e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8df0e08bc38fcf5b595d99fb9b7853ca70d4627d5db9cb7e2e010ad6cb97881e","first_computed_at":"2026-07-05T05:36:28.209529Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:36:28.209529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pOJzElZim0X1olcY27j3MMp+DOKJnyZY7LXw5enmuL6MskKzcPuzHmb/UTQDokuGj63Dyl3Ohbi0Z6h97iIEAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:36:28.210010Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.08412","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b460d2a5a358885474eb5ffb0680a4b0d2ca0676556809b51e64b21cb038de07","sha256:b183e7ce826711d022d71e1d748fe7261dc399aec9c976df09b17a6d01aa537a"],"state_sha256":"63b6fc92333f70e5fff4c8489b86c26fd91f5c89410a93b762d4fd50304cd134"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H7B01R2KalqDMVz6DLuPaIfD+qSnAYmN8oRACXzKGgBB6u6dBztL3uzDwpy2KN8iPs9e+zfnbU2B99QTBx1uCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T21:56:48.823527Z","bundle_sha256":"c2d7cfa1e89af4d357befde997e28fdf8d89c3eb16e02e6e427ab1c546ea1ea9"}}