{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DLX2JD7KSTTLTEUIZALXAICLTQ","short_pith_number":"pith:DLX2JD7K","schema_version":"1.0","canonical_sha256":"1aefa48fea94e6b99288c81770204b9c18ffc5a494d293d8b6f121ca18505133","source":{"kind":"arxiv","id":"2209.10081","version":4},"attestation_state":"computed","paper":{"title":"Revisiting Discrete Soft Actor-Critic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chao Yu, Deheng Ye, Haibin Zhou, Junliang Xing, Junyou Li, Li Shen, Tong Wei, Yuanchun Shi, Zichuan Lin","submitted_at":"2022-09-21T03:01:36Z","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"},"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":"2209.10081","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-21T03:01:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c273a25ecf2054d9d41bc45bb64250d4b8bac706e94c087ff636c9cd48059739","abstract_canon_sha256":"d4c2340aaa79ba29cb53838c21090a533c25f6e05c528e6ea3f1fee9d2266201"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:48.587665Z","signature_b64":"sjQl5QcfGOaqFhcl2BUqtyhMniAs7kON4TXjKrNAMxpcVLvsof4LnEjK2fYDT3lZwCrisWnZPUukC9GQXzMxCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1aefa48fea94e6b99288c81770204b9c18ffc5a494d293d8b6f121ca18505133","last_reissued_at":"2026-07-05T09:37:48.587160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:48.587160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Discrete Soft Actor-Critic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chao Yu, Deheng Ye, Haibin Zhou, Junliang Xing, Junyou Li, Li Shen, Tong Wei, Yuanchun Shi, Zichuan Lin","submitted_at":"2022-09-21T03:01:36Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.10081","kind":"arxiv","version":4},"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/2209.10081/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":"2209.10081","created_at":"2026-07-05T09:37:48.587219+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.10081v4","created_at":"2026-07-05T09:37:48.587219+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.10081","created_at":"2026-07-05T09:37:48.587219+00:00"},{"alias_kind":"pith_short_12","alias_value":"DLX2JD7KSTTL","created_at":"2026-07-05T09:37:48.587219+00:00"},{"alias_kind":"pith_short_16","alias_value":"DLX2JD7KSTTLTEUI","created_at":"2026-07-05T09:37:48.587219+00:00"},{"alias_kind":"pith_short_8","alias_value":"DLX2JD7K","created_at":"2026-07-05T09:37:48.587219+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.09838","citing_title":"Dissecting Discrete Soft Actor-Critic: Limitations and Principled Alternatives","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DLX2JD7KSTTLTEUIZALXAICLTQ","json":"https://pith.science/pith/DLX2JD7KSTTLTEUIZALXAICLTQ.json","graph_json":"https://pith.science/api/pith-number/DLX2JD7KSTTLTEUIZALXAICLTQ/graph.json","events_json":"https://pith.science/api/pith-number/DLX2JD7KSTTLTEUIZALXAICLTQ/events.json","paper":"https://pith.science/paper/DLX2JD7K"},"agent_actions":{"view_html":"https://pith.science/pith/DLX2JD7KSTTLTEUIZALXAICLTQ","download_json":"https://pith.science/pith/DLX2JD7KSTTLTEUIZALXAICLTQ.json","view_paper":"https://pith.science/paper/DLX2JD7K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.10081&json=true","fetch_graph":"https://pith.science/api/pith-number/DLX2JD7KSTTLTEUIZALXAICLTQ/graph.json","fetch_events":"https://pith.science/api/pith-number/DLX2JD7KSTTLTEUIZALXAICLTQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DLX2JD7KSTTLTEUIZALXAICLTQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DLX2JD7KSTTLTEUIZALXAICLTQ/action/storage_attestation","attest_author":"https://pith.science/pith/DLX2JD7KSTTLTEUIZALXAICLTQ/action/author_attestation","sign_citation":"https://pith.science/pith/DLX2JD7KSTTLTEUIZALXAICLTQ/action/citation_signature","submit_replication":"https://pith.science/pith/DLX2JD7KSTTLTEUIZALXAICLTQ/action/replication_record"}},"created_at":"2026-07-05T09:37:48.587219+00:00","updated_at":"2026-07-05T09:37:48.587219+00:00"}