{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:JITAOUYILT65BDVQ4KWJSUZZRM","short_pith_number":"pith:JITAOUYI","canonical_record":{"source":{"id":"1807.01736","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T18:41:27Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"28cd7e358620c7b9e503767b41d38dfbd39b9ce6a47e01fd875884dd75e1e71a","abstract_canon_sha256":"9733aa4a4394f65677125fdf939a43ef78e586c8637e5b5600d1f870cb290a96"},"schema_version":"1.0"},"canonical_sha256":"4a260753085cfdd08eb0e2ac9953398b3ce40467c765cd4582332611732b4cd6","source":{"kind":"arxiv","id":"1807.01736","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.01736","created_at":"2026-05-18T00:11:28Z"},{"alias_kind":"arxiv_version","alias_value":"1807.01736v1","created_at":"2026-05-18T00:11:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01736","created_at":"2026-05-18T00:11:28Z"},{"alias_kind":"pith_short_12","alias_value":"JITAOUYILT65","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"JITAOUYILT65BDVQ","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"JITAOUYI","created_at":"2026-05-18T12:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:JITAOUYILT65BDVQ4KWJSUZZRM","target":"record","payload":{"canonical_record":{"source":{"id":"1807.01736","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T18:41:27Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"28cd7e358620c7b9e503767b41d38dfbd39b9ce6a47e01fd875884dd75e1e71a","abstract_canon_sha256":"9733aa4a4394f65677125fdf939a43ef78e586c8637e5b5600d1f870cb290a96"},"schema_version":"1.0"},"canonical_sha256":"4a260753085cfdd08eb0e2ac9953398b3ce40467c765cd4582332611732b4cd6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:28.760808Z","signature_b64":"yVQ0XYMtb+4HeewOW9/TIhy6PFZ938dI2KJzHu4ZrwppOmsyXbqtJQT6dcV3/viQXX+GBYL7JqGeGKAAUWcgDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a260753085cfdd08eb0e2ac9953398b3ce40467c765cd4582332611732b4cd6","last_reissued_at":"2026-05-18T00:11:28.760413Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:28.760413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.01736","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":"2026-05-18T00:11:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oicVDw2Y0Qnjs6Q596A8HrfsqYFTDZGXisZ7NXYaEsQcoPIVk9Kh0UXVoHDL0BRW2Q1AAghID7yRj5xflkvBDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T12:01:29.765675Z"},"content_sha256":"000ee45dc74cca74710c1bd7b1c21e550cf76d502447e1369046dd1441f2abe5","schema_version":"1.0","event_id":"sha256:000ee45dc74cca74710c1bd7b1c21e550cf76d502447e1369046dd1441f2abe5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:JITAOUYILT65BDVQ4KWJSUZZRM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transfer with Model Features in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lucas Lehnert, Michael L. Littman","submitted_at":"2018-07-04T18:41:27Z","abstract_excerpt":"A key question in Reinforcement Learning is which representation an agent can learn to efficiently reuse knowledge between different tasks. Recently the Successor Representation was shown to have empirical benefits for transferring knowledge between tasks with shared transition dynamics. This paper presents Model Features: a feature representation that clusters behaviourally equivalent states and that is equivalent to a Model-Reduction. Further, we present a Successor Feature model which shows that learning Successor Features is equivalent to learning a Model-Reduction. A novel optimization ob"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01736","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":"2026-05-18T00:11:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x4YIXOIgXBRS8p8Kv9cx20apwYEZmUzyH2zlkaC1SPnKCfE778s2NyTocXqLK9emAEsa+tWLr0QYpPYdY+5sCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T12:01:29.766235Z"},"content_sha256":"18579e3435d3ca6a708c1d207f2c9e99cee82d2a374c808310452eefe52db180","schema_version":"1.0","event_id":"sha256:18579e3435d3ca6a708c1d207f2c9e99cee82d2a374c808310452eefe52db180"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JITAOUYILT65BDVQ4KWJSUZZRM/bundle.json","state_url":"https://pith.science/pith/JITAOUYILT65BDVQ4KWJSUZZRM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JITAOUYILT65BDVQ4KWJSUZZRM/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":"2026-05-26T12:01:29Z","links":{"resolver":"https://pith.science/pith/JITAOUYILT65BDVQ4KWJSUZZRM","bundle":"https://pith.science/pith/JITAOUYILT65BDVQ4KWJSUZZRM/bundle.json","state":"https://pith.science/pith/JITAOUYILT65BDVQ4KWJSUZZRM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JITAOUYILT65BDVQ4KWJSUZZRM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:JITAOUYILT65BDVQ4KWJSUZZRM","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":"9733aa4a4394f65677125fdf939a43ef78e586c8637e5b5600d1f870cb290a96","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T18:41:27Z","title_canon_sha256":"28cd7e358620c7b9e503767b41d38dfbd39b9ce6a47e01fd875884dd75e1e71a"},"schema_version":"1.0","source":{"id":"1807.01736","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.01736","created_at":"2026-05-18T00:11:28Z"},{"alias_kind":"arxiv_version","alias_value":"1807.01736v1","created_at":"2026-05-18T00:11:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01736","created_at":"2026-05-18T00:11:28Z"},{"alias_kind":"pith_short_12","alias_value":"JITAOUYILT65","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"JITAOUYILT65BDVQ","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"JITAOUYI","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:18579e3435d3ca6a708c1d207f2c9e99cee82d2a374c808310452eefe52db180","target":"graph","created_at":"2026-05-18T00:11:28Z","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":"A key question in Reinforcement Learning is which representation an agent can learn to efficiently reuse knowledge between different tasks. Recently the Successor Representation was shown to have empirical benefits for transferring knowledge between tasks with shared transition dynamics. This paper presents Model Features: a feature representation that clusters behaviourally equivalent states and that is equivalent to a Model-Reduction. Further, we present a Successor Feature model which shows that learning Successor Features is equivalent to learning a Model-Reduction. A novel optimization ob","authors_text":"Lucas Lehnert, Michael L. Littman","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T18:41:27Z","title":"Transfer with Model Features in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01736","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":"sha256:000ee45dc74cca74710c1bd7b1c21e550cf76d502447e1369046dd1441f2abe5","target":"record","created_at":"2026-05-18T00:11:28Z","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":"9733aa4a4394f65677125fdf939a43ef78e586c8637e5b5600d1f870cb290a96","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T18:41:27Z","title_canon_sha256":"28cd7e358620c7b9e503767b41d38dfbd39b9ce6a47e01fd875884dd75e1e71a"},"schema_version":"1.0","source":{"id":"1807.01736","kind":"arxiv","version":1}},"canonical_sha256":"4a260753085cfdd08eb0e2ac9953398b3ce40467c765cd4582332611732b4cd6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a260753085cfdd08eb0e2ac9953398b3ce40467c765cd4582332611732b4cd6","first_computed_at":"2026-05-18T00:11:28.760413Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:28.760413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yVQ0XYMtb+4HeewOW9/TIhy6PFZ938dI2KJzHu4ZrwppOmsyXbqtJQT6dcV3/viQXX+GBYL7JqGeGKAAUWcgDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:28.760808Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.01736","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:000ee45dc74cca74710c1bd7b1c21e550cf76d502447e1369046dd1441f2abe5","sha256:18579e3435d3ca6a708c1d207f2c9e99cee82d2a374c808310452eefe52db180"],"state_sha256":"126714374338c06dc2fdd9b5d204877e4f5e0ce0862fdaf84175ecdc2a4841f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e7qh6jbzHmNeN+L+esX7kpH9sw5Hu+gNebpb7w6pKZcVynQYbI6DwTkuFwiVqrG8o/+UjSkRcW5cUfikn9h3AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T12:01:29.768564Z","bundle_sha256":"7e6d7473a41720202c959988f0f0fa605e232030ed486cd46490c39e8b65ae04"}}