{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ZFDRAIU4QBSWKI2EKMQU7FKMMR","short_pith_number":"pith:ZFDRAIU4","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"},"canonical_sha256":"c94710229c806565234453214f954c6456f0ea737c8220921c4687321b9cefaf","source":{"kind":"arxiv","id":"1905.13420","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.13420","created_at":"2026-05-17T23:44:34Z"},{"alias_kind":"arxiv_version","alias_value":"1905.13420v1","created_at":"2026-05-17T23:44:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13420","created_at":"2026-05-17T23:44:34Z"},{"alias_kind":"pith_short_12","alias_value":"ZFDRAIU4QBSW","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZFDRAIU4QBSWKI2E","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZFDRAIU4","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ZFDRAIU4QBSWKI2EKMQU7FKMMR","target":"record","payload":{"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"},"canonical_sha256":"c94710229c806565234453214f954c6456f0ea737c8220921c4687321b9cefaf","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"},"source_kind":"arxiv","source_id":"1905.13420","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rz1iq/WNnDiwUKpUi9hjJ650xE5e6PsDoHKhfOjmdpcxo7w4S0RKWzOgeubKsetJx37702vxI7DisqngZegRDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T00:59:56.730607Z"},"content_sha256":"505a6445b9e355fe074c0d8087f7dea1aabcffbc46d5f371b1dcb76a1677d259","schema_version":"1.0","event_id":"sha256:505a6445b9e355fe074c0d8087f7dea1aabcffbc46d5f371b1dcb76a1677d259"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ZFDRAIU4QBSWKI2EKMQU7FKMMR","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mrp83qqbc5nqwFhJ1Wn6oQ1hP0k0tN4KliUn+G//z6fhVGJ6+io5vSi4s8GidyR50w20UPMVQHgqSqkT7AMqBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T00:59:56.731222Z"},"content_sha256":"6fa5e845da5bcef3981b6d99ef94bcc2634303beb6d3bb01efa5b5604b27a19b","schema_version":"1.0","event_id":"sha256:6fa5e845da5bcef3981b6d99ef94bcc2634303beb6d3bb01efa5b5604b27a19b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZFDRAIU4QBSWKI2EKMQU7FKMMR/bundle.json","state_url":"https://pith.science/pith/ZFDRAIU4QBSWKI2EKMQU7FKMMR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZFDRAIU4QBSWKI2EKMQU7FKMMR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-22T00:59:56Z","links":{"resolver":"https://pith.science/pith/ZFDRAIU4QBSWKI2EKMQU7FKMMR","bundle":"https://pith.science/pith/ZFDRAIU4QBSWKI2EKMQU7FKMMR/bundle.json","state":"https://pith.science/pith/ZFDRAIU4QBSWKI2EKMQU7FKMMR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZFDRAIU4QBSWKI2EKMQU7FKMMR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZFDRAIU4QBSWKI2EKMQU7FKMMR","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":"a01d8e481bc035001a39adf5dd59c95e811ecfb462639306519c6450ae7e7c4b","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-05-31T05:20:12Z","title_canon_sha256":"cae09812646e47b2fee76616b49ce875f9376eb660943fee47dd955d6df38387"},"schema_version":"1.0","source":{"id":"1905.13420","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.13420","created_at":"2026-05-17T23:44:34Z"},{"alias_kind":"arxiv_version","alias_value":"1905.13420v1","created_at":"2026-05-17T23:44:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13420","created_at":"2026-05-17T23:44:34Z"},{"alias_kind":"pith_short_12","alias_value":"ZFDRAIU4QBSW","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZFDRAIU4QBSWKI2E","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZFDRAIU4","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:6fa5e845da5bcef3981b6d99ef94bcc2634303beb6d3bb01efa5b5604b27a19b","target":"graph","created_at":"2026-05-17T23:44:34Z","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"},"paper":{"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 ","authors_text":"Jian Peng, Qiang Liu, Xi Chen, Yang Liu, Yuanyi Zhong, Yunan Luo","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-05-31T05:20:12Z","title":"Sequence Modeling of Temporal Credit Assignment for Episodic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13420","kind":"arxiv","version":1},"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":"sha256:505a6445b9e355fe074c0d8087f7dea1aabcffbc46d5f371b1dcb76a1677d259","target":"record","created_at":"2026-05-17T23:44:34Z","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":"a01d8e481bc035001a39adf5dd59c95e811ecfb462639306519c6450ae7e7c4b","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-05-31T05:20:12Z","title_canon_sha256":"cae09812646e47b2fee76616b49ce875f9376eb660943fee47dd955d6df38387"},"schema_version":"1.0","source":{"id":"1905.13420","kind":"arxiv","version":1}},"canonical_sha256":"c94710229c806565234453214f954c6456f0ea737c8220921c4687321b9cefaf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c94710229c806565234453214f954c6456f0ea737c8220921c4687321b9cefaf","first_computed_at":"2026-05-17T23:44:34.945308Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:34.945308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mp8/asPhrRFMW2xKw21BeCmlelFH3MXOVdTfTWPgoMO3Nhl9n+i13wKs3r1cmy9elOJ8FTqTwJKRLjYvTftLDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:34.945786Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.13420","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:505a6445b9e355fe074c0d8087f7dea1aabcffbc46d5f371b1dcb76a1677d259","sha256:6fa5e845da5bcef3981b6d99ef94bcc2634303beb6d3bb01efa5b5604b27a19b"],"state_sha256":"8f8d1bdd610affb97dd5eeb1a31e09e1eda559bb75818702a9fe66ffcee0ffce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vO6M5YBbS2Y97SZ1SiykK9xW0H/Tyna7iE5yirGpE3zW3I/H8lPEODXNu8YlFhVuZifLe6f4rBBZuolw/hGvCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T00:59:56.734112Z","bundle_sha256":"5e5ce3bda65de1be6793f567b0f4ef6ab0a2158cedc2892b7bd6c3d0e983e305"}}