{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6KITGLWOP6GDVMWY6QKXUVVCBN","short_pith_number":"pith:6KITGLWO","schema_version":"1.0","canonical_sha256":"f291332ece7f8c3ab2d8f4157a56a20b783eed379a98c17efbebec1940a73476","source":{"kind":"arxiv","id":"2305.11340","version":1},"attestation_state":"computed","paper":{"title":"Bayesian Reparameterization of Reward-Conditioned Reinforcement Learning with Energy-based Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Ding Zhao, Marco Pavone, Tong Che, Wenhao Ding","submitted_at":"2023-05-18T23:23:08Z","abstract_excerpt":"Recently, reward-conditioned reinforcement learning (RCRL) has gained popularity due to its simplicity, flexibility, and off-policy nature. However, we will show that current RCRL approaches are fundamentally limited and fail to address two critical challenges of RCRL -- improving generalization on high reward-to-go (RTG) inputs, and avoiding out-of-distribution (OOD) RTG queries during testing time. To address these challenges when training vanilla RCRL architectures, we propose Bayesian Reparameterized RCRL (BR-RCRL), a novel set of inductive biases for RCRL inspired by Bayes' theorem. BR-RC"},"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":"2305.11340","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-18T23:23:08Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"49cbae1af59efbc3770391f5ab526bd849b9d40121219212a10ebe42d5369191","abstract_canon_sha256":"e607d12ce91129aea33b9aa64bac3516cf69811db3d4d4b36007aa48e1ba14ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:35.901696Z","signature_b64":"LQQaUu7GxAdMMcSLheGIvEad9J7IaljtXvlVlHViupt9MYOqOrUUEU8wkxIDtTpqO2JmlZQdKZJmQxlBFsRZBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f291332ece7f8c3ab2d8f4157a56a20b783eed379a98c17efbebec1940a73476","last_reissued_at":"2026-07-05T06:11:35.901275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:35.901275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian Reparameterization of Reward-Conditioned Reinforcement Learning with Energy-based Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Ding Zhao, Marco Pavone, Tong Che, Wenhao Ding","submitted_at":"2023-05-18T23:23:08Z","abstract_excerpt":"Recently, reward-conditioned reinforcement learning (RCRL) has gained popularity due to its simplicity, flexibility, and off-policy nature. However, we will show that current RCRL approaches are fundamentally limited and fail to address two critical challenges of RCRL -- improving generalization on high reward-to-go (RTG) inputs, and avoiding out-of-distribution (OOD) RTG queries during testing time. To address these challenges when training vanilla RCRL architectures, we propose Bayesian Reparameterized RCRL (BR-RCRL), a novel set of inductive biases for RCRL inspired by Bayes' theorem. BR-RC"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11340","kind":"arxiv","version":1},"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/2305.11340/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":"2305.11340","created_at":"2026-07-05T06:11:35.901340+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11340v1","created_at":"2026-07-05T06:11:35.901340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11340","created_at":"2026-07-05T06:11:35.901340+00:00"},{"alias_kind":"pith_short_12","alias_value":"6KITGLWOP6GD","created_at":"2026-07-05T06:11:35.901340+00:00"},{"alias_kind":"pith_short_16","alias_value":"6KITGLWOP6GDVMWY","created_at":"2026-07-05T06:11:35.901340+00:00"},{"alias_kind":"pith_short_8","alias_value":"6KITGLWO","created_at":"2026-07-05T06:11:35.901340+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6KITGLWOP6GDVMWY6QKXUVVCBN","json":"https://pith.science/pith/6KITGLWOP6GDVMWY6QKXUVVCBN.json","graph_json":"https://pith.science/api/pith-number/6KITGLWOP6GDVMWY6QKXUVVCBN/graph.json","events_json":"https://pith.science/api/pith-number/6KITGLWOP6GDVMWY6QKXUVVCBN/events.json","paper":"https://pith.science/paper/6KITGLWO"},"agent_actions":{"view_html":"https://pith.science/pith/6KITGLWOP6GDVMWY6QKXUVVCBN","download_json":"https://pith.science/pith/6KITGLWOP6GDVMWY6QKXUVVCBN.json","view_paper":"https://pith.science/paper/6KITGLWO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11340&json=true","fetch_graph":"https://pith.science/api/pith-number/6KITGLWOP6GDVMWY6QKXUVVCBN/graph.json","fetch_events":"https://pith.science/api/pith-number/6KITGLWOP6GDVMWY6QKXUVVCBN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6KITGLWOP6GDVMWY6QKXUVVCBN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6KITGLWOP6GDVMWY6QKXUVVCBN/action/storage_attestation","attest_author":"https://pith.science/pith/6KITGLWOP6GDVMWY6QKXUVVCBN/action/author_attestation","sign_citation":"https://pith.science/pith/6KITGLWOP6GDVMWY6QKXUVVCBN/action/citation_signature","submit_replication":"https://pith.science/pith/6KITGLWOP6GDVMWY6QKXUVVCBN/action/replication_record"}},"created_at":"2026-07-05T06:11:35.901340+00:00","updated_at":"2026-07-05T06:11:35.901340+00:00"}