{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:X47VNZJ6Q6YEBXWDTKFDKEGGGH","short_pith_number":"pith:X47VNZJ6","schema_version":"1.0","canonical_sha256":"bf3f56e53e87b040dec39a8a3510c631dab8c140fe5aa6d474eaf45e79f04a88","source":{"kind":"arxiv","id":"2301.08940","version":2},"attestation_state":"computed","paper":{"title":"Quasi-optimal Reinforcement Learning with Continuous Actions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Ruoqing Zhu, Wenzhuo Zhou, Yuhan Li","submitted_at":"2023-01-21T11:30:13Z","abstract_excerpt":"Many real-world applications of reinforcement learning (RL) require making decisions in continuous action environments. In particular, determining the optimal dose level plays a vital role in developing medical treatment regimes. One challenge in adapting existing RL algorithms to medical applications, however, is that the popular infinite support stochastic policies, e.g., Gaussian policy, may assign riskily high dosages and harm patients seriously. Hence, it is important to induce a policy class whose support only contains near-optimal actions, and shrink the action-searching area for effect"},"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":"2301.08940","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-01-21T11:30:13Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"ac4287e35b25b657999031d25eaa37541cf132e51befa5ac3ac770e64574b448","abstract_canon_sha256":"ee7bf82767b3cc301b0026534769755423b6219ed6d06f047b1bae67cc9feed9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:51.593504Z","signature_b64":"K+a1Q8ItfZkFhBK6FyqL0D+tzp6qBKJNhwRBfeNvMcrRYND8uTAePPOgLMo9htxwm2GFvpTmk2fRSOWZwKxxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf3f56e53e87b040dec39a8a3510c631dab8c140fe5aa6d474eaf45e79f04a88","last_reissued_at":"2026-07-05T06:55:51.592995Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:51.592995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quasi-optimal Reinforcement Learning with Continuous Actions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Ruoqing Zhu, Wenzhuo Zhou, Yuhan Li","submitted_at":"2023-01-21T11:30:13Z","abstract_excerpt":"Many real-world applications of reinforcement learning (RL) require making decisions in continuous action environments. In particular, determining the optimal dose level plays a vital role in developing medical treatment regimes. One challenge in adapting existing RL algorithms to medical applications, however, is that the popular infinite support stochastic policies, e.g., Gaussian policy, may assign riskily high dosages and harm patients seriously. Hence, it is important to induce a policy class whose support only contains near-optimal actions, and shrink the action-searching area for effect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.08940","kind":"arxiv","version":2},"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/2301.08940/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":"2301.08940","created_at":"2026-07-05T06:55:51.593060+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.08940v2","created_at":"2026-07-05T06:55:51.593060+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.08940","created_at":"2026-07-05T06:55:51.593060+00:00"},{"alias_kind":"pith_short_12","alias_value":"X47VNZJ6Q6YE","created_at":"2026-07-05T06:55:51.593060+00:00"},{"alias_kind":"pith_short_16","alias_value":"X47VNZJ6Q6YEBXWD","created_at":"2026-07-05T06:55:51.593060+00:00"},{"alias_kind":"pith_short_8","alias_value":"X47VNZJ6","created_at":"2026-07-05T06:55:51.593060+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04187","citing_title":"Where to Intervene: Action Selection in Deep Reinforcement Learning","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X47VNZJ6Q6YEBXWDTKFDKEGGGH","json":"https://pith.science/pith/X47VNZJ6Q6YEBXWDTKFDKEGGGH.json","graph_json":"https://pith.science/api/pith-number/X47VNZJ6Q6YEBXWDTKFDKEGGGH/graph.json","events_json":"https://pith.science/api/pith-number/X47VNZJ6Q6YEBXWDTKFDKEGGGH/events.json","paper":"https://pith.science/paper/X47VNZJ6"},"agent_actions":{"view_html":"https://pith.science/pith/X47VNZJ6Q6YEBXWDTKFDKEGGGH","download_json":"https://pith.science/pith/X47VNZJ6Q6YEBXWDTKFDKEGGGH.json","view_paper":"https://pith.science/paper/X47VNZJ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.08940&json=true","fetch_graph":"https://pith.science/api/pith-number/X47VNZJ6Q6YEBXWDTKFDKEGGGH/graph.json","fetch_events":"https://pith.science/api/pith-number/X47VNZJ6Q6YEBXWDTKFDKEGGGH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X47VNZJ6Q6YEBXWDTKFDKEGGGH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X47VNZJ6Q6YEBXWDTKFDKEGGGH/action/storage_attestation","attest_author":"https://pith.science/pith/X47VNZJ6Q6YEBXWDTKFDKEGGGH/action/author_attestation","sign_citation":"https://pith.science/pith/X47VNZJ6Q6YEBXWDTKFDKEGGGH/action/citation_signature","submit_replication":"https://pith.science/pith/X47VNZJ6Q6YEBXWDTKFDKEGGGH/action/replication_record"}},"created_at":"2026-07-05T06:55:51.593060+00:00","updated_at":"2026-07-05T06:55:51.593060+00:00"}