{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:5BWGI6GBGAT3OGJQIVHKI7DW7E","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":"3adae2dbd67fe8e5c5819091b4edd4678f6db9c3143a3d231a27db6074dfe8ab","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-06-16T18:45:32Z","title_canon_sha256":"c472c5021cf9bbf55696334971c0f7acac52a2c7334313c12a618df4886ddd08"},"schema_version":"1.0","source":{"id":"1606.05312","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.05312","created_at":"2026-05-18T00:18:41Z"},{"alias_kind":"arxiv_version","alias_value":"1606.05312v2","created_at":"2026-05-18T00:18:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.05312","created_at":"2026-05-18T00:18:41Z"},{"alias_kind":"pith_short_12","alias_value":"5BWGI6GBGAT3","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_16","alias_value":"5BWGI6GBGAT3OGJQ","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_8","alias_value":"5BWGI6GB","created_at":"2026-05-18T12:29:58Z"}],"graph_snapshots":[{"event_id":"sha256:a5eb41b1627b5c79d4b4473e4cc69557fb86bee8271babf1579b00c393d67520","target":"graph","created_at":"2026-05-18T00:18:41Z","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"},"paper":{"abstract_excerpt":"Transfer in reinforcement learning refers to the notion that generalization should occur not only within a task but also across tasks. We propose a transfer framework for the scenario where the reward function changes between tasks but the environment's dynamics remain the same. Our approach rests on two key ideas: \"successor features\", a value function representation that decouples the dynamics of the environment from the rewards, and \"generalized policy improvement\", a generalization of dynamic programming's policy improvement operation that considers a set of policies rather than a single o","authors_text":"Andr\\'e Barreto, David Silver, Hado van Hasselt, Jonathan J. Hunt, R\\'emi Munos, Tom Schaul, Will Dabney","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-06-16T18:45:32Z","title":"Successor Features for Transfer in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.05312","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:ccf02ff02ed2f0129a3d1ea03ffef5aa50fc3c0360a0426ffe8a838f082b18c3","target":"record","created_at":"2026-05-18T00:18:41Z","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":"3adae2dbd67fe8e5c5819091b4edd4678f6db9c3143a3d231a27db6074dfe8ab","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-06-16T18:45:32Z","title_canon_sha256":"c472c5021cf9bbf55696334971c0f7acac52a2c7334313c12a618df4886ddd08"},"schema_version":"1.0","source":{"id":"1606.05312","kind":"arxiv","version":2}},"canonical_sha256":"e86c6478c13027b71930454ea47c76f92537826304c4d09cae6049d4a9a0f342","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e86c6478c13027b71930454ea47c76f92537826304c4d09cae6049d4a9a0f342","first_computed_at":"2026-05-18T00:18:41.726293Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:18:41.726293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A+UoNeuRi/Q1gGrPcByCMbMxIcUPz/gdR/z841C9748Ul5gpgCHF78q2lKnITixmzr5FVoAE31mLCCX5QPdzAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:18:41.726899Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.05312","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ccf02ff02ed2f0129a3d1ea03ffef5aa50fc3c0360a0426ffe8a838f082b18c3","sha256:a5eb41b1627b5c79d4b4473e4cc69557fb86bee8271babf1579b00c393d67520"],"state_sha256":"6c53e2f1138b327aac562d677cb14a8b352db432b93de82daafc959f31e0da7c"}