{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TN5XNVKK5ET2SDNVGRSSEGEZXK","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":"db9a4f914a476f417109570e2f14a88f513a4823ee0406042dc67f269cba8c7c","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-02T17:57:38Z","title_canon_sha256":"1433f852dc993506d236b23e7e2af8da62526e3349fcc215dbd137612ef3b86f"},"schema_version":"1.0","source":{"id":"2311.01450","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.01450","created_at":"2026-07-05T07:46:25Z"},{"alias_kind":"arxiv_version","alias_value":"2311.01450v2","created_at":"2026-07-05T07:46:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01450","created_at":"2026-07-05T07:46:25Z"},{"alias_kind":"pith_short_12","alias_value":"TN5XNVKK5ET2","created_at":"2026-07-05T07:46:25Z"},{"alias_kind":"pith_short_16","alias_value":"TN5XNVKK5ET2SDNV","created_at":"2026-07-05T07:46:25Z"},{"alias_kind":"pith_short_8","alias_value":"TN5XNVKK","created_at":"2026-07-05T07:46:25Z"}],"graph_snapshots":[{"event_id":"sha256:43f033936443b353209b14d11b70488bdd7e37fef58a02558303562c4bdcf1a7","target":"graph","created_at":"2026-07-05T07:46:25Z","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/2311.01450/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-based reinforcement learning (MBRL) has gained much attention for its ability to learn complex behaviors in a sample-efficient way: planning actions by generating imaginary trajectories with predicted rewards. Despite its success, we found that surprisingly, reward prediction is often a bottleneck of MBRL, especially for sparse rewards that are challenging (or even ambiguous) to predict. Motivated by the intuition that humans can learn from rough reward estimates, we propose a simple yet effective reward smoothing approach, DreamSmooth, which learns to predict a temporally-smoothed rewar","authors_text":"Pieter Abbeel, Vint Lee, Youngwoon Lee","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-02T17:57:38Z","title":"DreamSmooth: Improving Model-based Reinforcement Learning via Reward Smoothing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01450","kind":"arxiv","version":2},"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:f4beaed65964278f60947ae1434013e5f76d4c4688dddc77ba95923157e3b7c5","target":"record","created_at":"2026-07-05T07:46:25Z","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":"db9a4f914a476f417109570e2f14a88f513a4823ee0406042dc67f269cba8c7c","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-02T17:57:38Z","title_canon_sha256":"1433f852dc993506d236b23e7e2af8da62526e3349fcc215dbd137612ef3b86f"},"schema_version":"1.0","source":{"id":"2311.01450","kind":"arxiv","version":2}},"canonical_sha256":"9b7b76d54ae927a90db53465221899ba9bae0c668f95112a5a27d1612fdf2517","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b7b76d54ae927a90db53465221899ba9bae0c668f95112a5a27d1612fdf2517","first_computed_at":"2026-07-05T07:46:25.749304Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:46:25.749304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GDjHyIwLIgNWSUe9ioUl+XcI+KDLm3Edl7JvdoePxSgp9znGqlAGuo4mXfeE1bVe3zKub88MReGN4rcKs9dTBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:46:25.749817Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.01450","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4beaed65964278f60947ae1434013e5f76d4c4688dddc77ba95923157e3b7c5","sha256:43f033936443b353209b14d11b70488bdd7e37fef58a02558303562c4bdcf1a7"],"state_sha256":"716c7dabdd7041bbe31506cb4f6c791efc2941f2a5db0e3a6dcdb9b1850a3490"}