{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:XUFEW3QKFEWP3VRN2637BIK74K","short_pith_number":"pith:XUFEW3QK","canonical_record":{"source":{"id":"1912.05109","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-11T04:21:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3bd18fa6d9e51583a1a14d905e4a3db0d9001222db16add0df48eeb377046c5c","abstract_canon_sha256":"c020e637bfdb3315a558fa5b5c5da0ad484ecdbac591c86e0af70a13b7da4710"},"schema_version":"1.0"},"canonical_sha256":"bd0a4b6e0a292cfdd62dd7b7f0a15fe29e4c006248a03a843616425b86068d28","source":{"kind":"arxiv","id":"1912.05109","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.05109","created_at":"2026-07-05T00:25:32Z"},{"alias_kind":"arxiv_version","alias_value":"1912.05109v1","created_at":"2026-07-05T00:25:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.05109","created_at":"2026-07-05T00:25:32Z"},{"alias_kind":"pith_short_12","alias_value":"XUFEW3QKFEWP","created_at":"2026-07-05T00:25:32Z"},{"alias_kind":"pith_short_16","alias_value":"XUFEW3QKFEWP3VRN","created_at":"2026-07-05T00:25:32Z"},{"alias_kind":"pith_short_8","alias_value":"XUFEW3QK","created_at":"2026-07-05T00:25:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:XUFEW3QKFEWP3VRN2637BIK74K","target":"record","payload":{"canonical_record":{"source":{"id":"1912.05109","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-11T04:21:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3bd18fa6d9e51583a1a14d905e4a3db0d9001222db16add0df48eeb377046c5c","abstract_canon_sha256":"c020e637bfdb3315a558fa5b5c5da0ad484ecdbac591c86e0af70a13b7da4710"},"schema_version":"1.0"},"canonical_sha256":"bd0a4b6e0a292cfdd62dd7b7f0a15fe29e4c006248a03a843616425b86068d28","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:25:32.184641Z","signature_b64":"XgTHKU/mTtl7Mta7aqq3eDBqAq5jLwf0vjZFeBeifHSfzTP10CniF/W71Dz6KglPTH124B+eyMSKJ3DeOB+vAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd0a4b6e0a292cfdd62dd7b7f0a15fe29e4c006248a03a843616425b86068d28","last_reissued_at":"2026-07-05T00:25:32.184186Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:25:32.184186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.05109","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":"2026-07-05T00:25:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JqlKPMb9J6Z6sDzUcjA+o+NWFRDOIbWR5wAOoCp1pQ0Ym5gUvQfQWdEy9vxWmil5mGxfyGAwUMNgL+ZC+pBkDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:07:27.779357Z"},"content_sha256":"940cfc2bf3a66200945624cebaaadfee1d0eb04c3fc60c14467c774c72c2db27","schema_version":"1.0","event_id":"sha256:940cfc2bf3a66200945624cebaaadfee1d0eb04c3fc60c14467c774c72c2db27"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:XUFEW3QKFEWP3VRN2637BIK74K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Doubly Robust Off-Policy Actor-Critic Algorithms for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Doina Precup, Raihan Seraj, Riashat Islam, Samin Yeasar Arnob","submitted_at":"2019-12-11T04:21:47Z","abstract_excerpt":"We study the problem of off-policy critic evaluation in several variants of value-based off-policy actor-critic algorithms. Off-policy actor-critic algorithms require an off-policy critic evaluation step, to estimate the value of the new policy after every policy gradient update. Despite enormous success of off-policy policy gradients on control tasks, existing general methods suffer from high variance and instability, partly because the policy improvement depends on gradient of the estimated value function. In this work, we present a new way of off-policy policy evaluation in actor-critic, ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.05109","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/1912.05109/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":"2026-07-05T00:25:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hZwxZsNfXtfI7W6Sf9i1bMgT2ukK9V1ZF6RB2jqQyDduhvvLq5NOvAm7ru1iskvU/lTD0g4LvSXI07k32TEPAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:07:27.779924Z"},"content_sha256":"c06e79bddbd11d5afd9f128d2e54912f1adf2712a3177ba984c1684c360f3512","schema_version":"1.0","event_id":"sha256:c06e79bddbd11d5afd9f128d2e54912f1adf2712a3177ba984c1684c360f3512"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XUFEW3QKFEWP3VRN2637BIK74K/bundle.json","state_url":"https://pith.science/pith/XUFEW3QKFEWP3VRN2637BIK74K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XUFEW3QKFEWP3VRN2637BIK74K/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":"2026-08-06T08:07:27Z","links":{"resolver":"https://pith.science/pith/XUFEW3QKFEWP3VRN2637BIK74K","bundle":"https://pith.science/pith/XUFEW3QKFEWP3VRN2637BIK74K/bundle.json","state":"https://pith.science/pith/XUFEW3QKFEWP3VRN2637BIK74K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XUFEW3QKFEWP3VRN2637BIK74K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:XUFEW3QKFEWP3VRN2637BIK74K","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":"c020e637bfdb3315a558fa5b5c5da0ad484ecdbac591c86e0af70a13b7da4710","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-11T04:21:47Z","title_canon_sha256":"3bd18fa6d9e51583a1a14d905e4a3db0d9001222db16add0df48eeb377046c5c"},"schema_version":"1.0","source":{"id":"1912.05109","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.05109","created_at":"2026-07-05T00:25:32Z"},{"alias_kind":"arxiv_version","alias_value":"1912.05109v1","created_at":"2026-07-05T00:25:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.05109","created_at":"2026-07-05T00:25:32Z"},{"alias_kind":"pith_short_12","alias_value":"XUFEW3QKFEWP","created_at":"2026-07-05T00:25:32Z"},{"alias_kind":"pith_short_16","alias_value":"XUFEW3QKFEWP3VRN","created_at":"2026-07-05T00:25:32Z"},{"alias_kind":"pith_short_8","alias_value":"XUFEW3QK","created_at":"2026-07-05T00:25:32Z"}],"graph_snapshots":[{"event_id":"sha256:c06e79bddbd11d5afd9f128d2e54912f1adf2712a3177ba984c1684c360f3512","target":"graph","created_at":"2026-07-05T00:25:32Z","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/1912.05109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of off-policy critic evaluation in several variants of value-based off-policy actor-critic algorithms. Off-policy actor-critic algorithms require an off-policy critic evaluation step, to estimate the value of the new policy after every policy gradient update. Despite enormous success of off-policy policy gradients on control tasks, existing general methods suffer from high variance and instability, partly because the policy improvement depends on gradient of the estimated value function. In this work, we present a new way of off-policy policy evaluation in actor-critic, ba","authors_text":"Doina Precup, Raihan Seraj, Riashat Islam, Samin Yeasar Arnob","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-11T04:21:47Z","title":"Doubly Robust Off-Policy Actor-Critic Algorithms for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.05109","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":"sha256:940cfc2bf3a66200945624cebaaadfee1d0eb04c3fc60c14467c774c72c2db27","target":"record","created_at":"2026-07-05T00:25:32Z","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":"c020e637bfdb3315a558fa5b5c5da0ad484ecdbac591c86e0af70a13b7da4710","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-11T04:21:47Z","title_canon_sha256":"3bd18fa6d9e51583a1a14d905e4a3db0d9001222db16add0df48eeb377046c5c"},"schema_version":"1.0","source":{"id":"1912.05109","kind":"arxiv","version":1}},"canonical_sha256":"bd0a4b6e0a292cfdd62dd7b7f0a15fe29e4c006248a03a843616425b86068d28","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd0a4b6e0a292cfdd62dd7b7f0a15fe29e4c006248a03a843616425b86068d28","first_computed_at":"2026-07-05T00:25:32.184186Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:25:32.184186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XgTHKU/mTtl7Mta7aqq3eDBqAq5jLwf0vjZFeBeifHSfzTP10CniF/W71Dz6KglPTH124B+eyMSKJ3DeOB+vAg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:25:32.184641Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.05109","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:940cfc2bf3a66200945624cebaaadfee1d0eb04c3fc60c14467c774c72c2db27","sha256:c06e79bddbd11d5afd9f128d2e54912f1adf2712a3177ba984c1684c360f3512"],"state_sha256":"a3af39dcdc359c41a5e37e52d1ae570377024f62d12ddd5fa406281cd348e93a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TxYhhJVAigzytUopNODQXD6bSUYj3mlwm4jbJZ1sBu1CrgrBcCFPmT0f3xdk6om63HKciCzCGX5ZARFKGsUKAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T08:07:27.785454Z","bundle_sha256":"4005fb89a0eec93f155b9b540790a30c7d84446226edd7bdc5c19a081f304ab7"}}