{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OPQUOICWL4MZEDLD5CKYEB7UR2","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":"d9c42ef13559358c2f7f72c042be3e76ad87006bbffd878db5af0dabdc71bfb5","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-06T20:28:55Z","title_canon_sha256":"c127a099c224aebef5fe3c9fb0c7d4938b8abc96dd632488c5075fb40c37afb7"},"schema_version":"1.0","source":{"id":"2210.04642","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.04642","created_at":"2026-07-05T05:04:55Z"},{"alias_kind":"arxiv_version","alias_value":"2210.04642v1","created_at":"2026-07-05T05:04:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04642","created_at":"2026-07-05T05:04:55Z"},{"alias_kind":"pith_short_12","alias_value":"OPQUOICWL4MZ","created_at":"2026-07-05T05:04:55Z"},{"alias_kind":"pith_short_16","alias_value":"OPQUOICWL4MZEDLD","created_at":"2026-07-05T05:04:55Z"},{"alias_kind":"pith_short_8","alias_value":"OPQUOICW","created_at":"2026-07-05T05:04:55Z"}],"graph_snapshots":[{"event_id":"sha256:7714f9cfd7892f644a33020fb70077677b0dff1e9ee6345f63bc8b5f74a16470","target":"graph","created_at":"2026-07-05T05:04:55Z","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/2210.04642/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many potential applications of reinforcement learning (RL) are stymied by the large numbers of samples required to learn an effective policy. This is especially true when applying RL to real-world control tasks, e.g. in the sciences or robotics, where executing a policy in the environment is costly. In popular RL algorithms, agents typically explore either by adding stochasticity to a reward-maximizing policy or by attempting to gather maximal information about environment dynamics without taking the given task into account. In this work, we develop a method that allows us to plan for explorat","authors_text":"Ian Char, Jeff Schneider, Joseph Abbate, Mark D. Boyer, Rory Conlin, Stefano Ermon, Viraj Mehta, Willie Neiswanger","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-06T20:28:55Z","title":"Exploration via Planning for Information about the Optimal Trajectory"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04642","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:b7e5f50bbd20e02ae150b473d21877645488cd431a4c1eb065ff2e29bab73c52","target":"record","created_at":"2026-07-05T05:04:55Z","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":"d9c42ef13559358c2f7f72c042be3e76ad87006bbffd878db5af0dabdc71bfb5","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-06T20:28:55Z","title_canon_sha256":"c127a099c224aebef5fe3c9fb0c7d4938b8abc96dd632488c5075fb40c37afb7"},"schema_version":"1.0","source":{"id":"2210.04642","kind":"arxiv","version":1}},"canonical_sha256":"73e14720565f19920d63e8958207f48eb75df9df2f76d76c9f26e23854186436","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73e14720565f19920d63e8958207f48eb75df9df2f76d76c9f26e23854186436","first_computed_at":"2026-07-05T05:04:55.443538Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:04:55.443538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YCDt+NJgPeEy7zeWWatAdsVtnav5TdBLk3joqjemm6A2D+y8mgcbJZVpCeiUQY1sprzEMsoyFItlDZ+go0KJAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:04:55.443975Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.04642","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7e5f50bbd20e02ae150b473d21877645488cd431a4c1eb065ff2e29bab73c52","sha256:7714f9cfd7892f644a33020fb70077677b0dff1e9ee6345f63bc8b5f74a16470"],"state_sha256":"e4752af3aae4d3f9af46ed1c6bcedb3470220637c31bbfda49657c8108d256ef"}