{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SOBLDCG4JVEQISUTSRIXI6U436","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":"7e04e71a0e47a74d2958d700ac13d191432aa22be5ab2c345df5ac79137a0a0c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-28T05:34:53Z","title_canon_sha256":"98e76be976ca52a899d5b3f135881a0414e54ea617c1f447ea55a3e79408c284"},"schema_version":"1.0","source":{"id":"2306.15934","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.15934","created_at":"2026-07-05T06:25:46Z"},{"alias_kind":"arxiv_version","alias_value":"2306.15934v1","created_at":"2026-07-05T06:25:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.15934","created_at":"2026-07-05T06:25:46Z"},{"alias_kind":"pith_short_12","alias_value":"SOBLDCG4JVEQ","created_at":"2026-07-05T06:25:46Z"},{"alias_kind":"pith_short_16","alias_value":"SOBLDCG4JVEQISUT","created_at":"2026-07-05T06:25:46Z"},{"alias_kind":"pith_short_8","alias_value":"SOBLDCG4","created_at":"2026-07-05T06:25:46Z"}],"graph_snapshots":[{"event_id":"sha256:ed05af80ac258df384489a13f21c7dfb99ac7516139dd45f210722633c383620","target":"graph","created_at":"2026-07-05T06:25:46Z","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/2306.15934/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Agents must be able to adapt quickly as an environment changes. We find that existing model-based reinforcement learning agents are unable to do this well, in part because of how they use past experiences to train their world model. Here, we present Curious Replay -- a form of prioritized experience replay tailored to model-based agents through use of a curiosity-based priority signal. Agents using Curious Replay exhibit improved performance in an exploration paradigm inspired by animal behavior and on the Crafter benchmark. DreamerV3 with Curious Replay surpasses state-of-the-art performance ","authors_text":"Chris Doyle, Isaac Kauvar, Linqi Zhou, Nick Haber","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-28T05:34:53Z","title":"Curious Replay for Model-based Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.15934","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:fea75293d4f6c2b6f4d34aa5e5fde647f3e1f080d1446bc2b771f68c2621f447","target":"record","created_at":"2026-07-05T06:25:46Z","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":"7e04e71a0e47a74d2958d700ac13d191432aa22be5ab2c345df5ac79137a0a0c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-28T05:34:53Z","title_canon_sha256":"98e76be976ca52a899d5b3f135881a0414e54ea617c1f447ea55a3e79408c284"},"schema_version":"1.0","source":{"id":"2306.15934","kind":"arxiv","version":1}},"canonical_sha256":"9382b188dc4d49044a939451747a9cdfac50cbd60e97bd2e7e0327777b367135","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9382b188dc4d49044a939451747a9cdfac50cbd60e97bd2e7e0327777b367135","first_computed_at":"2026-07-05T06:25:46.608018Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:25:46.608018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AkCR+0MrqCwE/12mhFmqpp1q6k0DkPLvxvpMswHtejEyYQAK5mxdxQyN8bPTcH58+K4zU1bMC31J7W+6BDIpDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:25:46.608548Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.15934","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fea75293d4f6c2b6f4d34aa5e5fde647f3e1f080d1446bc2b771f68c2621f447","sha256:ed05af80ac258df384489a13f21c7dfb99ac7516139dd45f210722633c383620"],"state_sha256":"36a3d5566b184bac9503971ad4ed0e61ea45082cea0d9e15d470a011db7d5de5"}