{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MOFBSZKH2P7V4NAZD6GPUY3X3Z","short_pith_number":"pith:MOFBSZKH","schema_version":"1.0","canonical_sha256":"638a196547d3ff5e34191f8cfa6377de594d5bbee1c16888148b6753178a11a3","source":{"kind":"arxiv","id":"2506.16590","version":1},"attestation_state":"computed","paper":{"title":"Energy-Based Transfer for Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fiona Xie, Jasorsi Ghosh, Joseph Campbell, Katia Sycara, Yuzhe Lu, Zeyun Deng","submitted_at":"2025-06-19T20:25:52Z","abstract_excerpt":"Reinforcement learning algorithms often suffer from poor sample efficiency, making them challenging to apply in multi-task or continual learning settings. Efficiency can be improved by transferring knowledge from a previously trained teacher policy to guide exploration in new but related tasks. However, if the new task sufficiently differs from the teacher's training task, the transferred guidance may be sub-optimal and bias exploration toward low-reward behaviors. We propose an energy-based transfer learning method that uses out-of-distribution detection to selectively issue guidance, enablin"},"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":"2506.16590","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-19T20:25:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"259742c68445a797ac3274fc0237f50e9fd7f51d06b6875db24950ad19bebb89","abstract_canon_sha256":"38a0edec446e4a2941beb598878cfff741d3758cc5ca4f06070875a77c7f6ada"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:39.185300Z","signature_b64":"w0oyngoKIVcy4DApg6S+6uADCRxpVNFdxax/89Qz9DKuYJIZjOXCPCa6YpF3iKpQ9zA9toO3IFHiFdMab5+4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"638a196547d3ff5e34191f8cfa6377de594d5bbee1c16888148b6753178a11a3","last_reissued_at":"2026-07-05T11:24:39.184752Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:39.184752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Energy-Based Transfer for Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fiona Xie, Jasorsi Ghosh, Joseph Campbell, Katia Sycara, Yuzhe Lu, Zeyun Deng","submitted_at":"2025-06-19T20:25:52Z","abstract_excerpt":"Reinforcement learning algorithms often suffer from poor sample efficiency, making them challenging to apply in multi-task or continual learning settings. Efficiency can be improved by transferring knowledge from a previously trained teacher policy to guide exploration in new but related tasks. However, if the new task sufficiently differs from the teacher's training task, the transferred guidance may be sub-optimal and bias exploration toward low-reward behaviors. We propose an energy-based transfer learning method that uses out-of-distribution detection to selectively issue guidance, enablin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16590","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/2506.16590/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":"2506.16590","created_at":"2026-07-05T11:24:39.184812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.16590v1","created_at":"2026-07-05T11:24:39.184812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16590","created_at":"2026-07-05T11:24:39.184812+00:00"},{"alias_kind":"pith_short_12","alias_value":"MOFBSZKH2P7V","created_at":"2026-07-05T11:24:39.184812+00:00"},{"alias_kind":"pith_short_16","alias_value":"MOFBSZKH2P7V4NAZ","created_at":"2026-07-05T11:24:39.184812+00:00"},{"alias_kind":"pith_short_8","alias_value":"MOFBSZKH","created_at":"2026-07-05T11:24:39.184812+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/MOFBSZKH2P7V4NAZD6GPUY3X3Z","json":"https://pith.science/pith/MOFBSZKH2P7V4NAZD6GPUY3X3Z.json","graph_json":"https://pith.science/api/pith-number/MOFBSZKH2P7V4NAZD6GPUY3X3Z/graph.json","events_json":"https://pith.science/api/pith-number/MOFBSZKH2P7V4NAZD6GPUY3X3Z/events.json","paper":"https://pith.science/paper/MOFBSZKH"},"agent_actions":{"view_html":"https://pith.science/pith/MOFBSZKH2P7V4NAZD6GPUY3X3Z","download_json":"https://pith.science/pith/MOFBSZKH2P7V4NAZD6GPUY3X3Z.json","view_paper":"https://pith.science/paper/MOFBSZKH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.16590&json=true","fetch_graph":"https://pith.science/api/pith-number/MOFBSZKH2P7V4NAZD6GPUY3X3Z/graph.json","fetch_events":"https://pith.science/api/pith-number/MOFBSZKH2P7V4NAZD6GPUY3X3Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MOFBSZKH2P7V4NAZD6GPUY3X3Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MOFBSZKH2P7V4NAZD6GPUY3X3Z/action/storage_attestation","attest_author":"https://pith.science/pith/MOFBSZKH2P7V4NAZD6GPUY3X3Z/action/author_attestation","sign_citation":"https://pith.science/pith/MOFBSZKH2P7V4NAZD6GPUY3X3Z/action/citation_signature","submit_replication":"https://pith.science/pith/MOFBSZKH2P7V4NAZD6GPUY3X3Z/action/replication_record"}},"created_at":"2026-07-05T11:24:39.184812+00:00","updated_at":"2026-07-05T11:24:39.184812+00:00"}