{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:LGYWERFX2B2LW2OOGPWSYMG4LS","short_pith_number":"pith:LGYWERFX","canonical_record":{"source":{"id":"1901.10964","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-30T17:30:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a792c9919db3b16455c6c1e84c332c360c0b50822efad2f0cd340fbccd78d7a0","abstract_canon_sha256":"30c3e40d2b61e9665ad670117adad615e0e96baba687981420a67349f3d472fe"},"schema_version":"1.0"},"canonical_sha256":"59b16244b7d074bb69ce33ed2c30dc5cbeb9b3e3e164ca5d70568ed023bba1fe","source":{"kind":"arxiv","id":"1901.10964","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.10964","created_at":"2026-05-17T23:55:05Z"},{"alias_kind":"arxiv_version","alias_value":"1901.10964v1","created_at":"2026-05-17T23:55:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.10964","created_at":"2026-05-17T23:55:05Z"},{"alias_kind":"pith_short_12","alias_value":"LGYWERFX2B2L","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"LGYWERFX2B2LW2OO","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"LGYWERFX","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:LGYWERFX2B2LW2OOGPWSYMG4LS","target":"record","payload":{"canonical_record":{"source":{"id":"1901.10964","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-30T17:30:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a792c9919db3b16455c6c1e84c332c360c0b50822efad2f0cd340fbccd78d7a0","abstract_canon_sha256":"30c3e40d2b61e9665ad670117adad615e0e96baba687981420a67349f3d472fe"},"schema_version":"1.0"},"canonical_sha256":"59b16244b7d074bb69ce33ed2c30dc5cbeb9b3e3e164ca5d70568ed023bba1fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:05.665436Z","signature_b64":"cC/nB+ZGsLgn3BtRfYtFBXzakLh5oMBYtGWQhz1JiFWttqko1i2X/lA66B+OTTe5UMTIGh3A21sb+CCNyFZ+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59b16244b7d074bb69ce33ed2c30dc5cbeb9b3e3e164ca5d70568ed023bba1fe","last_reissued_at":"2026-05-17T23:55:05.664974Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:05.664974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.10964","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:55:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KZO/kBCKzbcvbUtZHaQa17V+3WJCsUCMpSIEEuAgbAoo7eNQ0AZHWGbzvLFGxEX0Va/He3vRX5ZLP+LYXYbaAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T00:17:26.576641Z"},"content_sha256":"d4fa91a6de724bd956f9f000aa4abcccf4a035b76e163be9df7182161710970a","schema_version":"1.0","event_id":"sha256:d4fa91a6de724bd956f9f000aa4abcccf4a035b76e163be9df7182161710970a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:LGYWERFX2B2LW2OOGPWSYMG4LS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andr\\'e Barreto, Augustin \\v{Z}\\'idek, Daniel Mankowitz, David Silver, Diana Borsa, John Quan, Matteo Hessel, R\\'emi Munos, Tom Schaul","submitted_at":"2019-01-30T17:30:31Z","abstract_excerpt":"The ability to transfer skills across tasks has the potential to scale up reinforcement learning (RL) agents to environments currently out of reach. Recently, a framework based on two ideas, successor features (SFs) and generalised policy improvement (GPI), has been introduced as a principled way of transferring skills. In this paper we extend the SFs & GPI framework in two ways. One of the basic assumptions underlying the original formulation of SFs & GPI is that rewards for all tasks of interest can be computed as linear combinations of a fixed set of features. We relax this constraint and s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.10964","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:55:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aaoEvxx4ZTE9kuQMb5W+W/SsOxa40jeua/xNlcFF2NKcE/p/2jWNh95oIykygTC0W9OnIIfJ8WqwSwqL1ywPBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T00:17:26.577292Z"},"content_sha256":"3ae98c0c9b717fb97225ef4a17e5c642a81346bbfc839288e0ab10a87024cff6","schema_version":"1.0","event_id":"sha256:3ae98c0c9b717fb97225ef4a17e5c642a81346bbfc839288e0ab10a87024cff6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LGYWERFX2B2LW2OOGPWSYMG4LS/bundle.json","state_url":"https://pith.science/pith/LGYWERFX2B2LW2OOGPWSYMG4LS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LGYWERFX2B2LW2OOGPWSYMG4LS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-02T00:17:26Z","links":{"resolver":"https://pith.science/pith/LGYWERFX2B2LW2OOGPWSYMG4LS","bundle":"https://pith.science/pith/LGYWERFX2B2LW2OOGPWSYMG4LS/bundle.json","state":"https://pith.science/pith/LGYWERFX2B2LW2OOGPWSYMG4LS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LGYWERFX2B2LW2OOGPWSYMG4LS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:LGYWERFX2B2LW2OOGPWSYMG4LS","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":"30c3e40d2b61e9665ad670117adad615e0e96baba687981420a67349f3d472fe","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-30T17:30:31Z","title_canon_sha256":"a792c9919db3b16455c6c1e84c332c360c0b50822efad2f0cd340fbccd78d7a0"},"schema_version":"1.0","source":{"id":"1901.10964","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.10964","created_at":"2026-05-17T23:55:05Z"},{"alias_kind":"arxiv_version","alias_value":"1901.10964v1","created_at":"2026-05-17T23:55:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.10964","created_at":"2026-05-17T23:55:05Z"},{"alias_kind":"pith_short_12","alias_value":"LGYWERFX2B2L","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"LGYWERFX2B2LW2OO","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"LGYWERFX","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:3ae98c0c9b717fb97225ef4a17e5c642a81346bbfc839288e0ab10a87024cff6","target":"graph","created_at":"2026-05-17T23:55:05Z","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":"The ability to transfer skills across tasks has the potential to scale up reinforcement learning (RL) agents to environments currently out of reach. Recently, a framework based on two ideas, successor features (SFs) and generalised policy improvement (GPI), has been introduced as a principled way of transferring skills. In this paper we extend the SFs & GPI framework in two ways. One of the basic assumptions underlying the original formulation of SFs & GPI is that rewards for all tasks of interest can be computed as linear combinations of a fixed set of features. We relax this constraint and s","authors_text":"Andr\\'e Barreto, Augustin \\v{Z}\\'idek, Daniel Mankowitz, David Silver, Diana Borsa, John Quan, Matteo Hessel, R\\'emi Munos, Tom Schaul","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-30T17:30:31Z","title":"Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.10964","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:d4fa91a6de724bd956f9f000aa4abcccf4a035b76e163be9df7182161710970a","target":"record","created_at":"2026-05-17T23:55:05Z","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":"30c3e40d2b61e9665ad670117adad615e0e96baba687981420a67349f3d472fe","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-30T17:30:31Z","title_canon_sha256":"a792c9919db3b16455c6c1e84c332c360c0b50822efad2f0cd340fbccd78d7a0"},"schema_version":"1.0","source":{"id":"1901.10964","kind":"arxiv","version":1}},"canonical_sha256":"59b16244b7d074bb69ce33ed2c30dc5cbeb9b3e3e164ca5d70568ed023bba1fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59b16244b7d074bb69ce33ed2c30dc5cbeb9b3e3e164ca5d70568ed023bba1fe","first_computed_at":"2026-05-17T23:55:05.664974Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:05.664974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cC/nB+ZGsLgn3BtRfYtFBXzakLh5oMBYtGWQhz1JiFWttqko1i2X/lA66B+OTTe5UMTIGh3A21sb+CCNyFZ+Ag==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:05.665436Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.10964","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4fa91a6de724bd956f9f000aa4abcccf4a035b76e163be9df7182161710970a","sha256:3ae98c0c9b717fb97225ef4a17e5c642a81346bbfc839288e0ab10a87024cff6"],"state_sha256":"b85af5a96e902053daa0d4e409af33abc043a4111a41a5908dafc6de6d98c2ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DMNclT9mFVeVQ4WS/OIjJ35YU4V7YDx3x2NRlA5Fh1/MVWh+qhwXAFKjFVbbPG8eWWsJ8C6HFDIqZbvnGDNYBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T00:17:26.580479Z","bundle_sha256":"1dbdc5e1103ef267d698556d0ccf2c7c1b2dd3f63c85ee3f915987e8be75f46a"}}