{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ZFDRAIU4QBSWKI2EKMQU7FKMMR","short_pith_number":"pith:ZFDRAIU4","schema_version":"1.0","canonical_sha256":"c94710229c806565234453214f954c6456f0ea737c8220921c4687321b9cefaf","source":{"kind":"arxiv","id":"1905.13420","version":1},"attestation_state":"computed","paper":{"title":"Sequence Modeling of Temporal Credit Assignment for Episodic Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jian Peng, Qiang Liu, Xi Chen, Yang Liu, Yuanyi Zhong, Yunan Luo","submitted_at":"2019-05-31T05:20:12Z","abstract_excerpt":"Recent advances in deep reinforcement learning algorithms have shown great potential and success for solving many challenging real-world problems, including Go game and robotic applications. Usually, these algorithms need a carefully designed reward function to guide training in each time step. However, in real world, it is non-trivial to design such a reward function, and the only signal available is usually obtained at the end of a trajectory, also known as the episodic reward or return. In this work, we introduce a new algorithm for temporal credit assignment, which learns to decompose the "},"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":"1905.13420","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-05-31T05:20:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"cae09812646e47b2fee76616b49ce875f9376eb660943fee47dd955d6df38387","abstract_canon_sha256":"a01d8e481bc035001a39adf5dd59c95e811ecfb462639306519c6450ae7e7c4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:34.945786Z","signature_b64":"mp8/asPhrRFMW2xKw21BeCmlelFH3MXOVdTfTWPgoMO3Nhl9n+i13wKs3r1cmy9elOJ8FTqTwJKRLjYvTftLDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c94710229c806565234453214f954c6456f0ea737c8220921c4687321b9cefaf","last_reissued_at":"2026-05-17T23:44:34.945308Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:34.945308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sequence Modeling of Temporal Credit Assignment for Episodic Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jian Peng, Qiang Liu, Xi Chen, Yang Liu, Yuanyi Zhong, Yunan Luo","submitted_at":"2019-05-31T05:20:12Z","abstract_excerpt":"Recent advances in deep reinforcement learning algorithms have shown great potential and success for solving many challenging real-world problems, including Go game and robotic applications. Usually, these algorithms need a carefully designed reward function to guide training in each time step. However, in real world, it is non-trivial to design such a reward function, and the only signal available is usually obtained at the end of a trajectory, also known as the episodic reward or return. In this work, we introduce a new algorithm for temporal credit assignment, which learns to decompose the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13420","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":""},"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":"1905.13420","created_at":"2026-05-17T23:44:34.945391+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.13420v1","created_at":"2026-05-17T23:44:34.945391+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13420","created_at":"2026-05-17T23:44:34.945391+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZFDRAIU4QBSW","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZFDRAIU4QBSWKI2E","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZFDRAIU4","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2106.01345","citing_title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZFDRAIU4QBSWKI2EKMQU7FKMMR","json":"https://pith.science/pith/ZFDRAIU4QBSWKI2EKMQU7FKMMR.json","graph_json":"https://pith.science/api/pith-number/ZFDRAIU4QBSWKI2EKMQU7FKMMR/graph.json","events_json":"https://pith.science/api/pith-number/ZFDRAIU4QBSWKI2EKMQU7FKMMR/events.json","paper":"https://pith.science/paper/ZFDRAIU4"},"agent_actions":{"view_html":"https://pith.science/pith/ZFDRAIU4QBSWKI2EKMQU7FKMMR","download_json":"https://pith.science/pith/ZFDRAIU4QBSWKI2EKMQU7FKMMR.json","view_paper":"https://pith.science/paper/ZFDRAIU4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.13420&json=true","fetch_graph":"https://pith.science/api/pith-number/ZFDRAIU4QBSWKI2EKMQU7FKMMR/graph.json","fetch_events":"https://pith.science/api/pith-number/ZFDRAIU4QBSWKI2EKMQU7FKMMR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZFDRAIU4QBSWKI2EKMQU7FKMMR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZFDRAIU4QBSWKI2EKMQU7FKMMR/action/storage_attestation","attest_author":"https://pith.science/pith/ZFDRAIU4QBSWKI2EKMQU7FKMMR/action/author_attestation","sign_citation":"https://pith.science/pith/ZFDRAIU4QBSWKI2EKMQU7FKMMR/action/citation_signature","submit_replication":"https://pith.science/pith/ZFDRAIU4QBSWKI2EKMQU7FKMMR/action/replication_record"}},"created_at":"2026-05-17T23:44:34.945391+00:00","updated_at":"2026-05-17T23:44:34.945391+00:00"}