{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TN5XNVKK5ET2SDNVGRSSEGEZXK","short_pith_number":"pith:TN5XNVKK","schema_version":"1.0","canonical_sha256":"9b7b76d54ae927a90db53465221899ba9bae0c668f95112a5a27d1612fdf2517","source":{"kind":"arxiv","id":"2311.01450","version":2},"attestation_state":"computed","paper":{"title":"DreamSmooth: Improving Model-based Reinforcement Learning via Reward Smoothing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Pieter Abbeel, Vint Lee, Youngwoon Lee","submitted_at":"2023-11-02T17:57:38Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2311.01450","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-02T17:57:38Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"1433f852dc993506d236b23e7e2af8da62526e3349fcc215dbd137612ef3b86f","abstract_canon_sha256":"db9a4f914a476f417109570e2f14a88f513a4823ee0406042dc67f269cba8c7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:25.749817Z","signature_b64":"GDjHyIwLIgNWSUe9ioUl+XcI+KDLm3Edl7JvdoePxSgp9znGqlAGuo4mXfeE1bVe3zKub88MReGN4rcKs9dTBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b7b76d54ae927a90db53465221899ba9bae0c668f95112a5a27d1612fdf2517","last_reissued_at":"2026-07-05T07:46:25.749304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:25.749304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DreamSmooth: Improving Model-based Reinforcement Learning via Reward Smoothing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Pieter Abbeel, Vint Lee, Youngwoon Lee","submitted_at":"2023-11-02T17:57:38Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01450","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2311.01450/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2311.01450","created_at":"2026-07-05T07:46:25.749380+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.01450v2","created_at":"2026-07-05T07:46:25.749380+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01450","created_at":"2026-07-05T07:46:25.749380+00:00"},{"alias_kind":"pith_short_12","alias_value":"TN5XNVKK5ET2","created_at":"2026-07-05T07:46:25.749380+00:00"},{"alias_kind":"pith_short_16","alias_value":"TN5XNVKK5ET2SDNV","created_at":"2026-07-05T07:46:25.749380+00:00"},{"alias_kind":"pith_short_8","alias_value":"TN5XNVKK","created_at":"2026-07-05T07:46:25.749380+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.02774","citing_title":"Learn A Flexible Exploration Model for Parameterized Action Markov Decision Processes","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TN5XNVKK5ET2SDNVGRSSEGEZXK","json":"https://pith.science/pith/TN5XNVKK5ET2SDNVGRSSEGEZXK.json","graph_json":"https://pith.science/api/pith-number/TN5XNVKK5ET2SDNVGRSSEGEZXK/graph.json","events_json":"https://pith.science/api/pith-number/TN5XNVKK5ET2SDNVGRSSEGEZXK/events.json","paper":"https://pith.science/paper/TN5XNVKK"},"agent_actions":{"view_html":"https://pith.science/pith/TN5XNVKK5ET2SDNVGRSSEGEZXK","download_json":"https://pith.science/pith/TN5XNVKK5ET2SDNVGRSSEGEZXK.json","view_paper":"https://pith.science/paper/TN5XNVKK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.01450&json=true","fetch_graph":"https://pith.science/api/pith-number/TN5XNVKK5ET2SDNVGRSSEGEZXK/graph.json","fetch_events":"https://pith.science/api/pith-number/TN5XNVKK5ET2SDNVGRSSEGEZXK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TN5XNVKK5ET2SDNVGRSSEGEZXK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TN5XNVKK5ET2SDNVGRSSEGEZXK/action/storage_attestation","attest_author":"https://pith.science/pith/TN5XNVKK5ET2SDNVGRSSEGEZXK/action/author_attestation","sign_citation":"https://pith.science/pith/TN5XNVKK5ET2SDNVGRSSEGEZXK/action/citation_signature","submit_replication":"https://pith.science/pith/TN5XNVKK5ET2SDNVGRSSEGEZXK/action/replication_record"}},"created_at":"2026-07-05T07:46:25.749380+00:00","updated_at":"2026-07-05T07:46:25.749380+00:00"}