{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:33T5Z6ZMWSDPC5S3I3R224NOMS","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":"8657057f5f03edac4298b961f60830338c0188b3a2ce48645190cad851d25b8b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-29T04:31:29Z","title_canon_sha256":"5583b891aa22c543c916f122408f192dba00b3824f8622763a0aa2a3835c89ed"},"schema_version":"1.0","source":{"id":"2205.14571","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.14571","created_at":"2026-07-05T05:44:24Z"},{"alias_kind":"arxiv_version","alias_value":"2205.14571v2","created_at":"2026-07-05T05:44:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14571","created_at":"2026-07-05T05:44:24Z"},{"alias_kind":"pith_short_12","alias_value":"33T5Z6ZMWSDP","created_at":"2026-07-05T05:44:24Z"},{"alias_kind":"pith_short_16","alias_value":"33T5Z6ZMWSDPC5S3","created_at":"2026-07-05T05:44:24Z"},{"alias_kind":"pith_short_8","alias_value":"33T5Z6ZM","created_at":"2026-07-05T05:44:24Z"}],"graph_snapshots":[{"event_id":"sha256:8085d049a7e39be1415a4d36664773d063b72b5377400169ee93719a6981e474","target":"graph","created_at":"2026-07-05T05:44:24Z","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/2205.14571/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of representational transfer in RL, where an agent first pretrains in a number of source tasks to discover a shared representation, which is subsequently used to learn a good policy in a \\emph{target task}. We propose a new notion of task relatedness between source and target tasks, and develop a novel approach for representational transfer under this assumption. Concretely, we show that given generative access to source tasks, we can discover a representation, using which subsequent linear RL techniques quickly converge to a near-optimal policy in the target task.\n  The s","authors_text":"Alekh Agarwal, Kaiwen Wang, Mengdi Wang, Wen Sun, Xuezhou Zhang, Yuda Song","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-29T04:31:29Z","title":"Provable Benefits of Representational Transfer in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14571","kind":"arxiv","version":2},"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":"sha256:5eb3cb611e33d9b2839e336c23b52b4276c86c3dc5d1549c4ce8cf5e2791203e","target":"record","created_at":"2026-07-05T05:44:24Z","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":"8657057f5f03edac4298b961f60830338c0188b3a2ce48645190cad851d25b8b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-29T04:31:29Z","title_canon_sha256":"5583b891aa22c543c916f122408f192dba00b3824f8622763a0aa2a3835c89ed"},"schema_version":"1.0","source":{"id":"2205.14571","kind":"arxiv","version":2}},"canonical_sha256":"dee7dcfb2cb486f1765b46e3ad71ae64aabd0189c19c419a45b5084f1165ac4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dee7dcfb2cb486f1765b46e3ad71ae64aabd0189c19c419a45b5084f1165ac4f","first_computed_at":"2026-07-05T05:44:24.473143Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:44:24.473143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0Ww2O4j3aSJXNkzmRuCTAYgFZCppxYvZLjonunm74OaBESzLsRI2tc/dXp2YwYyf3K4XanpIJoAD4W1/L/T3Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:44:24.473652Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.14571","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5eb3cb611e33d9b2839e336c23b52b4276c86c3dc5d1549c4ce8cf5e2791203e","sha256:8085d049a7e39be1415a4d36664773d063b72b5377400169ee93719a6981e474"],"state_sha256":"1ca73174940b84ba3fbf951a2928aaffd65c7217681a038bb3e42addef2b5ac9"}