{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DLX2JD7KSTTLTEUIZALXAICLTQ","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":"d4c2340aaa79ba29cb53838c21090a533c25f6e05c528e6ea3f1fee9d2266201","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-21T03:01:36Z","title_canon_sha256":"c273a25ecf2054d9d41bc45bb64250d4b8bac706e94c087ff636c9cd48059739"},"schema_version":"1.0","source":{"id":"2209.10081","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.10081","created_at":"2026-07-05T09:37:48Z"},{"alias_kind":"arxiv_version","alias_value":"2209.10081v4","created_at":"2026-07-05T09:37:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.10081","created_at":"2026-07-05T09:37:48Z"},{"alias_kind":"pith_short_12","alias_value":"DLX2JD7KSTTL","created_at":"2026-07-05T09:37:48Z"},{"alias_kind":"pith_short_16","alias_value":"DLX2JD7KSTTLTEUI","created_at":"2026-07-05T09:37:48Z"},{"alias_kind":"pith_short_8","alias_value":"DLX2JD7K","created_at":"2026-07-05T09:37:48Z"}],"graph_snapshots":[{"event_id":"sha256:157f072a18da038177979b9128e60539818868a4a188647d15c6ce175695d5d1","target":"graph","created_at":"2026-07-05T09:37:48Z","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/2209.10081/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the adaption of Soft Actor-Critic (SAC), which is considered as a state-of-the-art reinforcement learning (RL) algorithm, from continuous action space to discrete action space. We revisit vanilla discrete SAC and provide an in-depth understanding of its Q value underestimation and performance instability issues when applied to discrete settings. We thereby propose Stable Discrete SAC (SDSAC), an algorithm that leverages entropy-penalty and double average Q-learning with Q-clip to address these issues. Extensive experiments on typical benchmarks with discrete action space, including At","authors_text":"Chao Yu, Deheng Ye, Haibin Zhou, Junliang Xing, Junyou Li, Li Shen, Tong Wei, Yuanchun Shi, Zichuan Lin","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-21T03:01:36Z","title":"Revisiting Discrete Soft Actor-Critic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.10081","kind":"arxiv","version":4},"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:f80bc73224dbb45c2859e7644837b70cb897b551dfb1e5e666a2c3738090e4e2","target":"record","created_at":"2026-07-05T09:37:48Z","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":"d4c2340aaa79ba29cb53838c21090a533c25f6e05c528e6ea3f1fee9d2266201","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-21T03:01:36Z","title_canon_sha256":"c273a25ecf2054d9d41bc45bb64250d4b8bac706e94c087ff636c9cd48059739"},"schema_version":"1.0","source":{"id":"2209.10081","kind":"arxiv","version":4}},"canonical_sha256":"1aefa48fea94e6b99288c81770204b9c18ffc5a494d293d8b6f121ca18505133","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1aefa48fea94e6b99288c81770204b9c18ffc5a494d293d8b6f121ca18505133","first_computed_at":"2026-07-05T09:37:48.587160Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:37:48.587160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sjQl5QcfGOaqFhcl2BUqtyhMniAs7kON4TXjKrNAMxpcVLvsof4LnEjK2fYDT3lZwCrisWnZPUukC9GQXzMxCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:37:48.587665Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.10081","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f80bc73224dbb45c2859e7644837b70cb897b551dfb1e5e666a2c3738090e4e2","sha256:157f072a18da038177979b9128e60539818868a4a188647d15c6ce175695d5d1"],"state_sha256":"33c103988ec0c8ce0aea5d8ac09a2bf1b531d00f6011754fde970bbf8f41ab9f"}