{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PZPOGQSDWJPUQCQSC3W4OGZ6WM","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":"a321f28d542e97d2de036123c443be65f7786a4f007b49bc283d3b5b70d5d875","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T16:52:48Z","title_canon_sha256":"26c92a463060be2df82f2bfe371263d5b5b6df91d5a712cdd408ee5a24e8f6f6"},"schema_version":"1.0","source":{"id":"2310.05858","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05858","created_at":"2026-07-05T11:49:02Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05858v7","created_at":"2026-07-05T11:49:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05858","created_at":"2026-07-05T11:49:02Z"},{"alias_kind":"pith_short_12","alias_value":"PZPOGQSDWJPU","created_at":"2026-07-05T11:49:02Z"},{"alias_kind":"pith_short_16","alias_value":"PZPOGQSDWJPUQCQS","created_at":"2026-07-05T11:49:02Z"},{"alias_kind":"pith_short_8","alias_value":"PZPOGQSD","created_at":"2026-07-05T11:49:02Z"}],"graph_snapshots":[{"event_id":"sha256:6e140c6f2a0cf9a29ae5db63382ff19f19bdd2fa940df7724b7b20558a1b7762","target":"graph","created_at":"2026-07-05T11:49:02Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.05858/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bo Cheng, Chang Liu, Jiaxin Gao, Jingliang Duan, Keqiang Li, Liming Xiao, Shengbo Eben Li, Wenxuan Wang, Ya-Qin Zhang","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T16:52:48Z","title":"Distributional Soft Actor-Critic with Three Refinements"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05858","kind":"arxiv","version":7},"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:f6286f4f0742a865bfa1c6f9b34a363c967a6aee91dd8889dabffebef7cf5104","target":"record","created_at":"2026-07-05T11:49:02Z","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":"a321f28d542e97d2de036123c443be65f7786a4f007b49bc283d3b5b70d5d875","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T16:52:48Z","title_canon_sha256":"26c92a463060be2df82f2bfe371263d5b5b6df91d5a712cdd408ee5a24e8f6f6"},"schema_version":"1.0","source":{"id":"2310.05858","kind":"arxiv","version":7}},"canonical_sha256":"7e5ee34243b25f480a1216edc71b3eb33c7470c11d91523a61138227f22f3ca3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e5ee34243b25f480a1216edc71b3eb33c7470c11d91523a61138227f22f3ca3","first_computed_at":"2026-07-05T11:49:02.414994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:02.414994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3ftDHhe+NEBJSC1m0rIYW3fAFxPBGlJPtqXX1uMgdf76TkMbxSRNBvJHa1b3Q1U4ZlFegnrfUXD+vTNITvTnDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:02.415462Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.05858","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6286f4f0742a865bfa1c6f9b34a363c967a6aee91dd8889dabffebef7cf5104","sha256:6e140c6f2a0cf9a29ae5db63382ff19f19bdd2fa940df7724b7b20558a1b7762"],"state_sha256":"c7e3f0233769ec1cb22acff158fe84492c56298e4ffa63ff53b00f905f90bd6d"}