{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:4INW3W3AIMJSDI3ZZF2JRZV5Y3","short_pith_number":"pith:4INW3W3A","canonical_record":{"source":{"id":"1708.00102","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-07-31T23:36:18Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"2dacee0d80dab0547ef77a8cb53bd76d2c158696f1350c21049a5f13e2dd10e6","abstract_canon_sha256":"d0a2d54659c158a4e79fef186bf73fb571a69e321780dc8d7e3773333dabeec1"},"schema_version":"1.0"},"canonical_sha256":"e21b6ddb60431321a379c97498e6bdc6ff499a5f6fc68dffe6c554e5ac788418","source":{"kind":"arxiv","id":"1708.00102","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.00102","created_at":"2026-05-18T00:39:06Z"},{"alias_kind":"arxiv_version","alias_value":"1708.00102v1","created_at":"2026-05-18T00:39:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.00102","created_at":"2026-05-18T00:39:06Z"},{"alias_kind":"pith_short_12","alias_value":"4INW3W3AIMJS","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"4INW3W3AIMJSDI3Z","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"4INW3W3A","created_at":"2026-05-18T12:30:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:4INW3W3AIMJSDI3ZZF2JRZV5Y3","target":"record","payload":{"canonical_record":{"source":{"id":"1708.00102","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-07-31T23:36:18Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"2dacee0d80dab0547ef77a8cb53bd76d2c158696f1350c21049a5f13e2dd10e6","abstract_canon_sha256":"d0a2d54659c158a4e79fef186bf73fb571a69e321780dc8d7e3773333dabeec1"},"schema_version":"1.0"},"canonical_sha256":"e21b6ddb60431321a379c97498e6bdc6ff499a5f6fc68dffe6c554e5ac788418","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:06.037775Z","signature_b64":"bx7SIuKz9KumHokq54oc/tl+OJX9TmqaRgPlLzp4qXotFM7Eyfi1IH0LLcTx4O4R9bPnmMk/SooZBOBtt416Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e21b6ddb60431321a379c97498e6bdc6ff499a5f6fc68dffe6c554e5ac788418","last_reissued_at":"2026-05-18T00:39:06.037170Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:06.037170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.00102","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":"2026-05-18T00:39:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ok+2NI/tlhOWJGIB0WGnav8xZWgPPSqq8D6AcLfV5r/JDekAXD5X6M1qCmW6CuW03QipcjwxyoN3wiD1gBcyDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T01:20:21.611101Z"},"content_sha256":"b3ba2bc46348eeb03ed6b6c62ed467fbff9206a4031d56e17eebf4202a808d39","schema_version":"1.0","event_id":"sha256:b3ba2bc46348eeb03ed6b6c62ed467fbff9206a4031d56e17eebf4202a808d39"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:4INW3W3AIMJSDI3ZZF2JRZV5Y3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Advantages and Limitations of using Successor Features for Transfer in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Lucas Lehnert, Michael L. Littman, Stefanie Tellex","submitted_at":"2017-07-31T23:36:18Z","abstract_excerpt":"One question central to Reinforcement Learning is how to learn a feature representation that supports algorithm scaling and re-use of learned information from different tasks. Successor Features approach this problem by learning a feature representation that satisfies a temporal constraint. We present an implementation of an approach that decouples the feature representation from the reward function, making it suitable for transferring knowledge between domains. We then assess the advantages and limitations of using Successor Features for transfer."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.00102","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":"2026-05-18T00:39:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Gn3ebyj8QATx4Eupqfunp+1xLKNlSizssKb1HH89+kABd5z3TdT7hAwTquOd9BC8+TctM1Wu238jrq7CHGpCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T01:20:21.611766Z"},"content_sha256":"db563385df602491c5cd87ec34a0c4eebe73ccb8fe3dc107ad7188f655e4aea1","schema_version":"1.0","event_id":"sha256:db563385df602491c5cd87ec34a0c4eebe73ccb8fe3dc107ad7188f655e4aea1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4INW3W3AIMJSDI3ZZF2JRZV5Y3/bundle.json","state_url":"https://pith.science/pith/4INW3W3AIMJSDI3ZZF2JRZV5Y3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4INW3W3AIMJSDI3ZZF2JRZV5Y3/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":"2026-06-06T01:20:21Z","links":{"resolver":"https://pith.science/pith/4INW3W3AIMJSDI3ZZF2JRZV5Y3","bundle":"https://pith.science/pith/4INW3W3AIMJSDI3ZZF2JRZV5Y3/bundle.json","state":"https://pith.science/pith/4INW3W3AIMJSDI3ZZF2JRZV5Y3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4INW3W3AIMJSDI3ZZF2JRZV5Y3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:4INW3W3AIMJSDI3ZZF2JRZV5Y3","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":"d0a2d54659c158a4e79fef186bf73fb571a69e321780dc8d7e3773333dabeec1","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-07-31T23:36:18Z","title_canon_sha256":"2dacee0d80dab0547ef77a8cb53bd76d2c158696f1350c21049a5f13e2dd10e6"},"schema_version":"1.0","source":{"id":"1708.00102","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.00102","created_at":"2026-05-18T00:39:06Z"},{"alias_kind":"arxiv_version","alias_value":"1708.00102v1","created_at":"2026-05-18T00:39:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.00102","created_at":"2026-05-18T00:39:06Z"},{"alias_kind":"pith_short_12","alias_value":"4INW3W3AIMJS","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"4INW3W3AIMJSDI3Z","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"4INW3W3A","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:db563385df602491c5cd87ec34a0c4eebe73ccb8fe3dc107ad7188f655e4aea1","target":"graph","created_at":"2026-05-18T00:39:06Z","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":"One question central to Reinforcement Learning is how to learn a feature representation that supports algorithm scaling and re-use of learned information from different tasks. Successor Features approach this problem by learning a feature representation that satisfies a temporal constraint. We present an implementation of an approach that decouples the feature representation from the reward function, making it suitable for transferring knowledge between domains. We then assess the advantages and limitations of using Successor Features for transfer.","authors_text":"Lucas Lehnert, Michael L. Littman, Stefanie Tellex","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-07-31T23:36:18Z","title":"Advantages and Limitations of using Successor Features for Transfer in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.00102","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:b3ba2bc46348eeb03ed6b6c62ed467fbff9206a4031d56e17eebf4202a808d39","target":"record","created_at":"2026-05-18T00:39:06Z","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":"d0a2d54659c158a4e79fef186bf73fb571a69e321780dc8d7e3773333dabeec1","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-07-31T23:36:18Z","title_canon_sha256":"2dacee0d80dab0547ef77a8cb53bd76d2c158696f1350c21049a5f13e2dd10e6"},"schema_version":"1.0","source":{"id":"1708.00102","kind":"arxiv","version":1}},"canonical_sha256":"e21b6ddb60431321a379c97498e6bdc6ff499a5f6fc68dffe6c554e5ac788418","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e21b6ddb60431321a379c97498e6bdc6ff499a5f6fc68dffe6c554e5ac788418","first_computed_at":"2026-05-18T00:39:06.037170Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:39:06.037170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bx7SIuKz9KumHokq54oc/tl+OJX9TmqaRgPlLzp4qXotFM7Eyfi1IH0LLcTx4O4R9bPnmMk/SooZBOBtt416Bw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:39:06.037775Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.00102","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3ba2bc46348eeb03ed6b6c62ed467fbff9206a4031d56e17eebf4202a808d39","sha256:db563385df602491c5cd87ec34a0c4eebe73ccb8fe3dc107ad7188f655e4aea1"],"state_sha256":"4a55ec85f8f631d56fe625d3db273b408155225a418e7a65f4ab6527f3b706ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SIQ6kRmwxfRZ2hu4a5Py0eGsGc9/5xdRJUjqsiF0JKtYBPrEuCaIRzY3/jisv12reHNNBLFDZunoK7e3MxP9Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T01:20:21.614790Z","bundle_sha256":"3213ed2b08e39b2d19acd0b5a60fd269f0b38ee58e6de2a8871cff9d3dd64b13"}}