{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EHTP2TUTJ45BGLI6SXFWBFHNRM","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":"4da774a01f4dd6e86b6a6da9fa97be9ab9731223f1202d26e3edd85726740c32","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-10T22:27:21Z","title_canon_sha256":"efb27f3886a1ce3f3c51e7fecfc4dfb5665dc70fa782eb5a7184b331b243b572"},"schema_version":"1.0","source":{"id":"2403.06328","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06328","created_at":"2026-07-05T10:02:22Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06328v4","created_at":"2026-07-05T10:02:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06328","created_at":"2026-07-05T10:02:22Z"},{"alias_kind":"pith_short_12","alias_value":"EHTP2TUTJ45B","created_at":"2026-07-05T10:02:22Z"},{"alias_kind":"pith_short_16","alias_value":"EHTP2TUTJ45BGLI6","created_at":"2026-07-05T10:02:22Z"},{"alias_kind":"pith_short_8","alias_value":"EHTP2TUT","created_at":"2026-07-05T10:02:22Z"}],"graph_snapshots":[{"event_id":"sha256:48e368eb7a9a25dd0b3e5a6f725fe6bbdf0d9d781ae992a374bb7a8a07599dba","target":"graph","created_at":"2026-07-05T10:02:22Z","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/2403.06328/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Intelligent agents must be generalists, capable of quickly adapting to various tasks. In reinforcement learning (RL), model-based RL learns a dynamics model of the world, in principle enabling transfer to arbitrary reward functions through planning. However, autoregressive model rollouts suffer from compounding error, making model-based RL ineffective for long-horizon problems. Successor features offer an alternative by modeling a policy's long-term state occupancy, reducing policy evaluation under new rewards to linear regression. Yet, zero-shot policy optimization for new tasks with successo","authors_text":"Abhishek Gupta, Chuning Zhu, Simon S. Du, Tyler Han, Xinqi Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-10T22:27:21Z","title":"Distributional Successor Features Enable Zero-Shot Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06328","kind":"arxiv","version":4},"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":"sha256:276abb4a031e29cc17b3a7cbdec87d833d72ca7914a67b5c41527fdcd5d3aaad","target":"record","created_at":"2026-07-05T10:02:22Z","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":"4da774a01f4dd6e86b6a6da9fa97be9ab9731223f1202d26e3edd85726740c32","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-10T22:27:21Z","title_canon_sha256":"efb27f3886a1ce3f3c51e7fecfc4dfb5665dc70fa782eb5a7184b331b243b572"},"schema_version":"1.0","source":{"id":"2403.06328","kind":"arxiv","version":4}},"canonical_sha256":"21e6fd4e934f3a132d1e95cb6094ed8b0fbec879868388e9ed508e7396cf605b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21e6fd4e934f3a132d1e95cb6094ed8b0fbec879868388e9ed508e7396cf605b","first_computed_at":"2026-07-05T10:02:22.730275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:22.730275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V1ZOlK9doCH16/485wpipqN9oNs+mItwp/olisjCQnhRHtj7RZmZRuK/JXKRPmsvTQfQs+Bgbty7NQZrb4JhDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:22.730713Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.06328","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:276abb4a031e29cc17b3a7cbdec87d833d72ca7914a67b5c41527fdcd5d3aaad","sha256:48e368eb7a9a25dd0b3e5a6f725fe6bbdf0d9d781ae992a374bb7a8a07599dba"],"state_sha256":"552a1fe9ee709605600417362d84fa6ed70a153a760fbb40cef91d46d2a6b529"}