{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:BHQFDYQ2RTFWVTYAKRI7G74UWI","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":"7edf47029291ba308a8ace796f21d0a8e98d5b5aad6934bfaaa22dee2edff7c1","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-16T17:54:41Z","title_canon_sha256":"38086df4404bc2a7ae68618bd5ae7153e26e52005051f55df074ef5d29987275"},"schema_version":"1.0","source":{"id":"2006.09359","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.09359","created_at":"2026-07-05T02:34:40Z"},{"alias_kind":"arxiv_version","alias_value":"2006.09359v6","created_at":"2026-07-05T02:34:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.09359","created_at":"2026-07-05T02:34:40Z"},{"alias_kind":"pith_short_12","alias_value":"BHQFDYQ2RTFW","created_at":"2026-07-05T02:34:40Z"},{"alias_kind":"pith_short_16","alias_value":"BHQFDYQ2RTFWVTYA","created_at":"2026-07-05T02:34:40Z"},{"alias_kind":"pith_short_8","alias_value":"BHQFDYQ2","created_at":"2026-07-05T02:34:40Z"}],"graph_snapshots":[{"event_id":"sha256:d30eca42f15365308884cd7cab5b1a31f1ba875f8a071e5ea4e4342f1640ddce","target":"graph","created_at":"2026-07-05T02:34:40Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our method, advantage weighted actor critic (AWAC), enables rapid learning of skills with a combination of prior demonstration data and online experience."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That offline data (expert or sub-optimal) can be leveraged via AWAC to bootstrap online RL without the typical difficulties in transitioning from offline to online training remaining insurmountable."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"AWAC combines offline data with online RL via advantage-weighted actor-critic updates to enable faster acquisition of robotic skills such as dexterous manipulation."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"AWAC combines offline data with online reinforcement learning to accelerate policy improvement for robotic control."}],"snapshot_sha256":"e6c6f9aea8f84eddca047d174c1f67e477db374f3ebb05a4541e9d6356e17014"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ce12733f1ca213ba25889a848a3babd844807356c3da06d368173def46f2c7a8"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2006.09359/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) provides an appealing formalism for learning control policies from experience. However, the classic active formulation of RL necessitates a lengthy active exploration process for each behavior, making it difficult to apply in real-world settings such as robotic control. If we can instead allow RL algorithms to effectively use previously collected data to aid the online learning process, such applications could be made substantially more practical: the prior data would provide a starting point that mitigates challenges due to exploration and sample complexity, while ","authors_text":"Abhishek Gupta, Ashvin Nair, Murtaza Dalal, Sergey Levine","cross_cats":["cs.RO","stat.ML"],"headline":"AWAC combines offline data with online reinforcement learning to accelerate policy improvement for robotic control.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-16T17:54:41Z","title":"AWAC: Accelerating Online Reinforcement Learning with Offline Datasets"},"references":{"count":68,"internal_anchors":1,"resolved_work":68,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Apprenticeship learning via inverse reinforcement learning","work_id":"55f5d70f-5791-410a-a5b1-939094feb422","year":2004},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Maximum a Posteriori Policy Optimisation","work_id":"9317bc09-2729-4016-870c-ed365cd5acfc","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"An Optimistic Perspective on Offline Reinforce- ment Learning","work_id":"189fbeac-cf4a-4029-8af1-8f6d322576bf","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"ROBEL: Robotics Benchmarks for Learning with Low- Cost Robots","work_id":"3747b14e-b759-4712-b12e-754105ca6191","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Robot Learning From Demonstration","work_id":"0f19df2c-c43a-475e-b93e-bda79a70b173","year":1997}],"snapshot_sha256":"14c42ef49f296fe18b1a5fe7559f5e58d15f9680f32b88eb914d1075354688f3"},"source":{"id":"2006.09359","kind":"arxiv","version":6},"verdict":{"created_at":"2026-05-13T03:28:40.431855Z","id":"1463b969-c79f-42f6-bb2e-086f13c19d3f","model_set":{"reader":"grok-4.3"},"one_line_summary":"AWAC combines offline data with online RL via advantage-weighted actor-critic updates to enable faster acquisition of robotic skills such as dexterous manipulation.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"AWAC combines offline data with online reinforcement learning to accelerate policy improvement for robotic control.","strongest_claim":"Our method, advantage weighted actor critic (AWAC), enables rapid learning of skills with a combination of prior demonstration data and online experience.","weakest_assumption":"That offline data (expert or sub-optimal) can be leveraged via AWAC to bootstrap online RL without the typical difficulties in transitioning from offline to online training remaining insurmountable."}},"verdict_id":"1463b969-c79f-42f6-bb2e-086f13c19d3f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6a3e8e819caf292bb3faf19c79d96fa72a8aba88441e1e75bb872a927deb350c","target":"record","created_at":"2026-07-05T02:34:40Z","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":"7edf47029291ba308a8ace796f21d0a8e98d5b5aad6934bfaaa22dee2edff7c1","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-16T17:54:41Z","title_canon_sha256":"38086df4404bc2a7ae68618bd5ae7153e26e52005051f55df074ef5d29987275"},"schema_version":"1.0","source":{"id":"2006.09359","kind":"arxiv","version":6}},"canonical_sha256":"09e051e21a8ccb6acf005451f37f94b213a0d6416acab0368a6b78956a12c20d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09e051e21a8ccb6acf005451f37f94b213a0d6416acab0368a6b78956a12c20d","first_computed_at":"2026-07-05T02:34:40.161435Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:34:40.161435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iqZyKHR0lODin9DZxejjz4PDfZM8SzPXIb4UiWSOMRuC30WuBcwRWEEGsJTWZ76XrgrhhPoer8v2WEoOGc+CBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:34:40.161882Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.09359","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a3e8e819caf292bb3faf19c79d96fa72a8aba88441e1e75bb872a927deb350c","sha256:d30eca42f15365308884cd7cab5b1a31f1ba875f8a071e5ea4e4342f1640ddce"],"state_sha256":"b6b8161893037df4f75699c3d4621acfb0ca5dc6f0db7a10992d40b2ef12c599"}