{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:OWSWQ33USXHY5BKQP2EUWR33RE","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":"c952bc8ed6b04b3d7f4802b4b4934b60e05d8c2afed6327e32e1f48f38efbff8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2020-04-30T02:23:15Z","title_canon_sha256":"f42cd5a95bf2f2fc8938cfbf56f96852a86868d912d488daaa4b3dc2eb3e6845"},"schema_version":"1.0","source":{"id":"2004.14547","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14547","created_at":"2026-07-05T11:28:27Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14547v3","created_at":"2026-07-05T11:28:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14547","created_at":"2026-07-05T11:28:27Z"},{"alias_kind":"pith_short_12","alias_value":"OWSWQ33USXHY","created_at":"2026-07-05T11:28:27Z"},{"alias_kind":"pith_short_16","alias_value":"OWSWQ33USXHY5BKQ","created_at":"2026-07-05T11:28:27Z"},{"alias_kind":"pith_short_8","alias_value":"OWSWQ33U","created_at":"2026-07-05T11:28:27Z"}],"graph_snapshots":[{"event_id":"sha256:6414091a59939deb5a499e4085a2aaa06fc71d2bce8a32295a42b8c0af73b074","target":"graph","created_at":"2026-07-05T11:28:27Z","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/2004.14547/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Distributional Soft Actor-Critic (DSAC), a distributional reinforcement learning (RL) algorithm that combines the strengths of distributional information of accumulated rewards and entropy-driven exploration from Soft Actor-Critic (SAC) algorithm. DSAC models the randomness in both action and rewards, surpassing baseline performances on various continuous control tasks. Unlike standard approaches that solely maximize expected rewards, we propose a unified framework for risk-sensitive learning, one that optimizes the risk-related objective while balancing entropy to encourage explora","authors_text":"Jun Yang, Junyao Chen, Li Xia, Qianchuan Zhao, Xiaoteng Ma, Zhengyuan Zhou","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2020-04-30T02:23:15Z","title":"DSAC: Distributional Soft Actor-Critic for Risk-Sensitive Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14547","kind":"arxiv","version":3},"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":"sha256:9220d88bd56f33cee606f7cf4df15f2e4fca5af2221efc3b6b1fe2a29868b83d","target":"record","created_at":"2026-07-05T11:28:27Z","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":"c952bc8ed6b04b3d7f4802b4b4934b60e05d8c2afed6327e32e1f48f38efbff8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2020-04-30T02:23:15Z","title_canon_sha256":"f42cd5a95bf2f2fc8938cfbf56f96852a86868d912d488daaa4b3dc2eb3e6845"},"schema_version":"1.0","source":{"id":"2004.14547","kind":"arxiv","version":3}},"canonical_sha256":"75a5686f7495cf8e85507e894b477b89199b255d020a6bc979b62e6a8a02d2e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75a5686f7495cf8e85507e894b477b89199b255d020a6bc979b62e6a8a02d2e2","first_computed_at":"2026-07-05T11:28:27.682459Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:27.682459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TbRfCY3h5nkS4xrRl57IzCYJAt5dyRTwcNZe8RsHXs7PjvNNxwv7D4os6AMw5UnUNgZaH1KnNIpjdItwJTYbAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:27.682935Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.14547","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9220d88bd56f33cee606f7cf4df15f2e4fca5af2221efc3b6b1fe2a29868b83d","sha256:6414091a59939deb5a499e4085a2aaa06fc71d2bce8a32295a42b8c0af73b074"],"state_sha256":"29d255efdcf51f89b83e45c5e3116eefaa3a9393aa108df001aa87ec9c66eb01"}