{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:VKQG7Z3TFTUGLN7OI3C6JQWSAY","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":"0a38c47d312f57888d4437da4c306e310ab230232d74827cdf8af60d298c9697","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-14T03:38:38Z","title_canon_sha256":"15e56ba74df2585a1cf8e70f2e99e26f12a9e44b9232977e51e80115b90fa277"},"schema_version":"1.0","source":{"id":"2011.07213","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.07213","created_at":"2026-07-05T01:51:47Z"},{"alias_kind":"arxiv_version","alias_value":"2011.07213v1","created_at":"2026-07-05T01:51:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.07213","created_at":"2026-07-05T01:51:47Z"},{"alias_kind":"pith_short_12","alias_value":"VKQG7Z3TFTUG","created_at":"2026-07-05T01:51:47Z"},{"alias_kind":"pith_short_16","alias_value":"VKQG7Z3TFTUGLN7O","created_at":"2026-07-05T01:51:47Z"},{"alias_kind":"pith_short_8","alias_value":"VKQG7Z3T","created_at":"2026-07-05T01:51:47Z"}],"graph_snapshots":[{"event_id":"sha256:b20c76269a0942d41b4208e29c4b1b20bee0a4805fd01bc945e8e7510c087f2a","target":"graph","created_at":"2026-07-05T01:51:47Z","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/2011.07213/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of offline reinforcement learning is to learn a policy from a fixed dataset, without further interactions with the environment. This setting will be an increasingly more important paradigm for real-world applications of reinforcement learning such as robotics, in which data collection is slow and potentially dangerous. Existing off-policy algorithms have limited performance on static datasets due to extrapolation errors from out-of-distribution actions. This leads to the challenge of constraining the policy to select actions within the support of the dataset during training. We propos","authors_text":"David Held, Sujay Bajracharya, Wenxuan Zhou","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-14T03:38:38Z","title":"PLAS: Latent Action Space for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.07213","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":"sha256:75a02ad6b13aa80ed9e875eee8105b250c7faece53fc973c97cd47f89c87ff53","target":"record","created_at":"2026-07-05T01:51:47Z","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":"0a38c47d312f57888d4437da4c306e310ab230232d74827cdf8af60d298c9697","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-14T03:38:38Z","title_canon_sha256":"15e56ba74df2585a1cf8e70f2e99e26f12a9e44b9232977e51e80115b90fa277"},"schema_version":"1.0","source":{"id":"2011.07213","kind":"arxiv","version":1}},"canonical_sha256":"aaa06fe7732ce865b7ee46c5e4c2d2063590d419fa6fa45228d1e97eb18ada11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aaa06fe7732ce865b7ee46c5e4c2d2063590d419fa6fa45228d1e97eb18ada11","first_computed_at":"2026-07-05T01:51:47.196499Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:51:47.196499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HMBJb0mT6qFQwNxDK+zkuEBJef7KwLp/tUyhP/J3XunXELOSPf5enxn7v9y7XmXBRRsXOZad0hAz//yxp3unBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:51:47.196856Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.07213","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75a02ad6b13aa80ed9e875eee8105b250c7faece53fc973c97cd47f89c87ff53","sha256:b20c76269a0942d41b4208e29c4b1b20bee0a4805fd01bc945e8e7510c087f2a"],"state_sha256":"347f119321f40793c089d2f6329ca111839c5cd240d1d588ad89684da314922b"}