{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TPLRLP6GLLCRKSWEGLLU3GDZ3T","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":"24ac25b12908af9d0c732f4364bd8547574215380bc8964aae83ec852c7ec725","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-06T16:56:25Z","title_canon_sha256":"e0caad1b0c6e2ec64e65f1950296913eaea173557666fad1075464aff76ea8a9"},"schema_version":"1.0","source":{"id":"2107.02729","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.02729","created_at":"2026-07-05T04:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"2107.02729v4","created_at":"2026-07-05T04:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.02729","created_at":"2026-07-05T04:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"TPLRLP6GLLCR","created_at":"2026-07-05T04:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"TPLRLP6GLLCRKSWE","created_at":"2026-07-05T04:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"TPLRLP6G","created_at":"2026-07-05T04:05:12Z"}],"graph_snapshots":[{"event_id":"sha256:fa7acdea3f21da4b792b4ea517f12ba714547284af5ac531b4970cd019daa490","target":"graph","created_at":"2026-07-05T04:05:12Z","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/2107.02729/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One practical challenge in reinforcement learning (RL) is how to make quick adaptations when faced with new environments. In this paper, we propose a principled framework for adaptive RL, called \\textit{AdaRL}, that adapts reliably and efficiently to changes across domains with a few samples from the target domain, even in partially observable environments. Specifically, we leverage a parsimonious graphical representation that characterizes structural relationships over variables in the RL system. Such graphical representations provide a compact way to encode what and where the changes across ","authors_text":"Biwei Huang, Chaochao Lu, Fan Feng, Kun Zhang, Sara Magliacane","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-06T16:56:25Z","title":"AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.02729","kind":"arxiv","version":4},"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:c50c7adcaca7820c0784a66051a47844bbb5418be4381428e0d12f8c18bf5c40","target":"record","created_at":"2026-07-05T04:05:12Z","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":"24ac25b12908af9d0c732f4364bd8547574215380bc8964aae83ec852c7ec725","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-06T16:56:25Z","title_canon_sha256":"e0caad1b0c6e2ec64e65f1950296913eaea173557666fad1075464aff76ea8a9"},"schema_version":"1.0","source":{"id":"2107.02729","kind":"arxiv","version":4}},"canonical_sha256":"9bd715bfc65ac5154ac432d74d9879dcc40b4a5b8a9063a814f1891130d1737a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9bd715bfc65ac5154ac432d74d9879dcc40b4a5b8a9063a814f1891130d1737a","first_computed_at":"2026-07-05T04:05:12.228149Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:05:12.228149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sKUTIhYI9O+udS4EtMk7CabN6KmyqK2Xw8a/LEnr5TvjYzJrQcZ6PvYoXW5LNTKtocvDx7XfE/8nhMW8+C2RDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:05:12.228648Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.02729","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c50c7adcaca7820c0784a66051a47844bbb5418be4381428e0d12f8c18bf5c40","sha256:fa7acdea3f21da4b792b4ea517f12ba714547284af5ac531b4970cd019daa490"],"state_sha256":"db382ed37794c7d3dbdeb6fe80d0e96b4ad5bb1b26ce7c660284b7fffee21262"}