{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PZPOGQSDWJPUQCQSC3W4OGZ6WM","short_pith_number":"pith:PZPOGQSD","schema_version":"1.0","canonical_sha256":"7e5ee34243b25f480a1216edc71b3eb33c7470c11d91523a61138227f22f3ca3","source":{"kind":"arxiv","id":"2310.05858","version":7},"attestation_state":"computed","paper":{"title":"Distributional Soft Actor-Critic with Three Refinements","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Bo Cheng, Chang Liu, Jiaxin Gao, Jingliang Duan, Keqiang Li, Liming Xiao, Shengbo Eben Li, Wenxuan Wang, Ya-Qin Zhang","submitted_at":"2023-10-09T16:52:48Z","abstract_excerpt":"Reinforcement learning (RL) has shown remarkable success in solving complex decision-making and control tasks. However, many model-free RL algorithms experience performance degradation due to inaccurate value estimation, particularly the overestimation of Q-values, which can lead to suboptimal policies. To address this issue, we previously proposed the Distributional Soft Actor-Critic (DSAC or DSACv1), an off-policy RL algorithm that enhances value estimation accuracy by learning a continuous Gaussian value distribution. Despite its effectiveness, DSACv1 faces challenges such as training insta"},"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":"2310.05858","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T16:52:48Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"26c92a463060be2df82f2bfe371263d5b5b6df91d5a712cdd408ee5a24e8f6f6","abstract_canon_sha256":"a321f28d542e97d2de036123c443be65f7786a4f007b49bc283d3b5b70d5d875"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:02.415462Z","signature_b64":"3ftDHhe+NEBJSC1m0rIYW3fAFxPBGlJPtqXX1uMgdf76TkMbxSRNBvJHa1b3Q1U4ZlFegnrfUXD+vTNITvTnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e5ee34243b25f480a1216edc71b3eb33c7470c11d91523a61138227f22f3ca3","last_reissued_at":"2026-07-05T11:49:02.414994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:02.414994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributional Soft Actor-Critic with Three Refinements","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Bo Cheng, Chang Liu, Jiaxin Gao, Jingliang Duan, Keqiang Li, Liming Xiao, Shengbo Eben Li, Wenxuan Wang, Ya-Qin Zhang","submitted_at":"2023-10-09T16:52:48Z","abstract_excerpt":"Reinforcement learning (RL) has shown remarkable success in solving complex decision-making and control tasks. However, many model-free RL algorithms experience performance degradation due to inaccurate value estimation, particularly the overestimation of Q-values, which can lead to suboptimal policies. To address this issue, we previously proposed the Distributional Soft Actor-Critic (DSAC or DSACv1), an off-policy RL algorithm that enhances value estimation accuracy by learning a continuous Gaussian value distribution. Despite its effectiveness, DSACv1 faces challenges such as training insta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05858","kind":"arxiv","version":7},"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/2310.05858/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":"2310.05858","created_at":"2026-07-05T11:49:02.415058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.05858v7","created_at":"2026-07-05T11:49:02.415058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05858","created_at":"2026-07-05T11:49:02.415058+00:00"},{"alias_kind":"pith_short_12","alias_value":"PZPOGQSDWJPU","created_at":"2026-07-05T11:49:02.415058+00:00"},{"alias_kind":"pith_short_16","alias_value":"PZPOGQSDWJPUQCQS","created_at":"2026-07-05T11:49:02.415058+00:00"},{"alias_kind":"pith_short_8","alias_value":"PZPOGQSD","created_at":"2026-07-05T11:49:02.415058+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/PZPOGQSDWJPUQCQSC3W4OGZ6WM","json":"https://pith.science/pith/PZPOGQSDWJPUQCQSC3W4OGZ6WM.json","graph_json":"https://pith.science/api/pith-number/PZPOGQSDWJPUQCQSC3W4OGZ6WM/graph.json","events_json":"https://pith.science/api/pith-number/PZPOGQSDWJPUQCQSC3W4OGZ6WM/events.json","paper":"https://pith.science/paper/PZPOGQSD"},"agent_actions":{"view_html":"https://pith.science/pith/PZPOGQSDWJPUQCQSC3W4OGZ6WM","download_json":"https://pith.science/pith/PZPOGQSDWJPUQCQSC3W4OGZ6WM.json","view_paper":"https://pith.science/paper/PZPOGQSD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.05858&json=true","fetch_graph":"https://pith.science/api/pith-number/PZPOGQSDWJPUQCQSC3W4OGZ6WM/graph.json","fetch_events":"https://pith.science/api/pith-number/PZPOGQSDWJPUQCQSC3W4OGZ6WM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PZPOGQSDWJPUQCQSC3W4OGZ6WM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PZPOGQSDWJPUQCQSC3W4OGZ6WM/action/storage_attestation","attest_author":"https://pith.science/pith/PZPOGQSDWJPUQCQSC3W4OGZ6WM/action/author_attestation","sign_citation":"https://pith.science/pith/PZPOGQSDWJPUQCQSC3W4OGZ6WM/action/citation_signature","submit_replication":"https://pith.science/pith/PZPOGQSDWJPUQCQSC3W4OGZ6WM/action/replication_record"}},"created_at":"2026-07-05T11:49:02.415058+00:00","updated_at":"2026-07-05T11:49:02.415058+00:00"}