{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:YEJ7P5NBJ6YV36GC7HC67ONEUY","short_pith_number":"pith:YEJ7P5NB","schema_version":"1.0","canonical_sha256":"c113f7f5a14fb15df8c2f9c5efb9a4a609c07fc3946aa6404d33323caee55fb9","source":{"kind":"arxiv","id":"1905.11100","version":1},"attestation_state":"computed","paper":{"title":"Disentangling Dynamics and Returns: Value Function Decomposition with Future Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Guangyong Chen, Hongyao Tang, Jianye Hao, Li Wang, Pengfei Chen, Yaodong Yang, Zhaopeng Meng","submitted_at":"2019-05-27T10:15:42Z","abstract_excerpt":"Value functions are crucial for model-free Reinforcement Learning (RL) to obtain a policy implicitly or guide the policy updates. Value estimation heavily depends on the stochasticity of environmental dynamics and the quality of reward signals. In this paper, we propose a two-step understanding of value estimation from the perspective of future prediction, through decomposing the value function into a reward-independent future dynamics part and a policy-independent trajectory return part. We then derive a practical deep RL algorithm from the above decomposition, consisting of a convolutional t"},"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":"1905.11100","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T10:15:42Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"29da048efbe6565cb1760f34bad3d8cd11167266530009cfb443515f637efbdc","abstract_canon_sha256":"95f7b3506d7d8d227cf024675f55ca2f760a8175b7c1977ba5d701b9f98a2e76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:02.942572Z","signature_b64":"jfnZCsVGdcbGPHHQBtL+BJIsNZeRmQRoexL4JqqracBR1pRw9brDUBfHxfzRvFIZIJFUAgbkf/ujHsmsMDIuCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c113f7f5a14fb15df8c2f9c5efb9a4a609c07fc3946aa6404d33323caee55fb9","last_reissued_at":"2026-05-17T23:45:02.942037Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:02.942037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disentangling Dynamics and Returns: Value Function Decomposition with Future Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Guangyong Chen, Hongyao Tang, Jianye Hao, Li Wang, Pengfei Chen, Yaodong Yang, Zhaopeng Meng","submitted_at":"2019-05-27T10:15:42Z","abstract_excerpt":"Value functions are crucial for model-free Reinforcement Learning (RL) to obtain a policy implicitly or guide the policy updates. Value estimation heavily depends on the stochasticity of environmental dynamics and the quality of reward signals. In this paper, we propose a two-step understanding of value estimation from the perspective of future prediction, through decomposing the value function into a reward-independent future dynamics part and a policy-independent trajectory return part. We then derive a practical deep RL algorithm from the above decomposition, consisting of a convolutional t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11100","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":"1905.11100","created_at":"2026-05-17T23:45:02.942119+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.11100v1","created_at":"2026-05-17T23:45:02.942119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11100","created_at":"2026-05-17T23:45:02.942119+00:00"},{"alias_kind":"pith_short_12","alias_value":"YEJ7P5NBJ6YV","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"YEJ7P5NBJ6YV36GC","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"YEJ7P5NB","created_at":"2026-05-18T12:33:33.725879+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/YEJ7P5NBJ6YV36GC7HC67ONEUY","json":"https://pith.science/pith/YEJ7P5NBJ6YV36GC7HC67ONEUY.json","graph_json":"https://pith.science/api/pith-number/YEJ7P5NBJ6YV36GC7HC67ONEUY/graph.json","events_json":"https://pith.science/api/pith-number/YEJ7P5NBJ6YV36GC7HC67ONEUY/events.json","paper":"https://pith.science/paper/YEJ7P5NB"},"agent_actions":{"view_html":"https://pith.science/pith/YEJ7P5NBJ6YV36GC7HC67ONEUY","download_json":"https://pith.science/pith/YEJ7P5NBJ6YV36GC7HC67ONEUY.json","view_paper":"https://pith.science/paper/YEJ7P5NB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.11100&json=true","fetch_graph":"https://pith.science/api/pith-number/YEJ7P5NBJ6YV36GC7HC67ONEUY/graph.json","fetch_events":"https://pith.science/api/pith-number/YEJ7P5NBJ6YV36GC7HC67ONEUY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YEJ7P5NBJ6YV36GC7HC67ONEUY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YEJ7P5NBJ6YV36GC7HC67ONEUY/action/storage_attestation","attest_author":"https://pith.science/pith/YEJ7P5NBJ6YV36GC7HC67ONEUY/action/author_attestation","sign_citation":"https://pith.science/pith/YEJ7P5NBJ6YV36GC7HC67ONEUY/action/citation_signature","submit_replication":"https://pith.science/pith/YEJ7P5NBJ6YV36GC7HC67ONEUY/action/replication_record"}},"created_at":"2026-05-17T23:45:02.942119+00:00","updated_at":"2026-05-17T23:45:02.942119+00:00"}