{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:QUBRG33WY73TP4UBW67BJ3KXBJ","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":"e86f00bb34deaa00b7526f7ee3eb367235c271837b8514d6ce959a162acee428","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-14T23:16:20Z","title_canon_sha256":"5a512305b6df7ab8c2e3581e4f4271957c1fed11fa0d952054e52326500a6223"},"schema_version":"1.0","source":{"id":"2006.08051","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.08051","created_at":"2026-07-05T01:10:17Z"},{"alias_kind":"arxiv_version","alias_value":"2006.08051v1","created_at":"2026-07-05T01:10:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.08051","created_at":"2026-07-05T01:10:17Z"},{"alias_kind":"pith_short_12","alias_value":"QUBRG33WY73T","created_at":"2026-07-05T01:10:17Z"},{"alias_kind":"pith_short_16","alias_value":"QUBRG33WY73TP4UB","created_at":"2026-07-05T01:10:17Z"},{"alias_kind":"pith_short_8","alias_value":"QUBRG33W","created_at":"2026-07-05T01:10:17Z"}],"graph_snapshots":[{"event_id":"sha256:0b3ebbe6f9cb624ba892b2db3c523430bf9bf115f4a1be0ded86d05efaa8d792","target":"graph","created_at":"2026-07-05T01:10:17Z","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/2006.08051/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The high sample complexity of reinforcement learning challenges its use in practice. A promising approach is to quickly adapt pre-trained policies to new environments. Existing methods for this policy adaptation problem typically rely on domain randomization and meta-learning, by sampling from some distribution of target environments during pre-training, and thus face difficulty on out-of-distribution target environments. We propose new model-based mechanisms that are able to make online adaptation in unseen target environments, by combining ideas from no-regret online learning and adaptive co","authors_text":"Aditi Mavalankar, Sicun Gao, Wen Sun, Yuda Song","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-14T23:16:20Z","title":"Provably Efficient Model-based Policy Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.08051","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:cdd36a8e3896c8bb900141e7f100da6ffe9b997994a20cbc781f2440a0217585","target":"record","created_at":"2026-07-05T01:10:17Z","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":"e86f00bb34deaa00b7526f7ee3eb367235c271837b8514d6ce959a162acee428","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-14T23:16:20Z","title_canon_sha256":"5a512305b6df7ab8c2e3581e4f4271957c1fed11fa0d952054e52326500a6223"},"schema_version":"1.0","source":{"id":"2006.08051","kind":"arxiv","version":1}},"canonical_sha256":"8503136f76c7f737f281b7be14ed570a405b2ada8a3e9d59ae3842653151dd2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8503136f76c7f737f281b7be14ed570a405b2ada8a3e9d59ae3842653151dd2c","first_computed_at":"2026-07-05T01:10:17.871040Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:10:17.871040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/VTEByIWOvhPg7C6jFHjsS6JiFIkTE6o9nS/vxGh2hdDm1Ev9yqC461ryM93eyeHmzT3GV99zMkdBU/W0ZphAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:10:17.871519Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.08051","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cdd36a8e3896c8bb900141e7f100da6ffe9b997994a20cbc781f2440a0217585","sha256:0b3ebbe6f9cb624ba892b2db3c523430bf9bf115f4a1be0ded86d05efaa8d792"],"state_sha256":"db81aed21564539d1fdc33710a12208c14ea25bd12af4681dd48d126ed025dcd"}