{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TSTO6BRDXBDB4ZAAJS64QMQ6W5","short_pith_number":"pith:TSTO6BRD","schema_version":"1.0","canonical_sha256":"9ca6ef0623b8461e64004cbdc8321eb74584d0eeff8bebf2cc4792d145d304be","source":{"kind":"arxiv","id":"2510.20152","version":4},"attestation_state":"computed","paper":{"title":"Soft Switching Expert Policies for Controlling Systems with Uncertain Parameters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Junya Ikemoto","submitted_at":"2025-10-23T03:00:04Z","abstract_excerpt":"This paper proposes a simulation-based reinforcement learning algorithm for controlling systems with uncertain and varying system parameters. While simulators are useful for safely learning control policies, the reality gap remains a major challenge. To alleviate this challenge, we propose a two-stage algorithm. First, multiple control policies are learned for systems with different system parameters in a simulator. Second, for a real system, the control policies are adaptively switched using an online convex optimization algorithm based on observations. This approach is expected to reduce lea"},"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":"2510.20152","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2025-10-23T03:00:04Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"811d80d5b8fb49a54c074874e3f926b4e8a09c9dcfbe6a20c640af3a83d0ed5d","abstract_canon_sha256":"b27d02767b8257f5fe6e3837762718f35a2a0ca162c80f43dfa53ddcb2077b7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:33.739817Z","signature_b64":"KNYqZbuwGDwXW3RtTZxmORQfObcp2CZn5e1fXn1vnoSRFjUYh5o9/yuKD8tAwaXL6jJS8baZHe8CdjzG9fWXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ca6ef0623b8461e64004cbdc8321eb74584d0eeff8bebf2cc4792d145d304be","last_reissued_at":"2026-05-18T03:09:33.739378Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:33.739378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Soft Switching Expert Policies for Controlling Systems with Uncertain Parameters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Junya Ikemoto","submitted_at":"2025-10-23T03:00:04Z","abstract_excerpt":"This paper proposes a simulation-based reinforcement learning algorithm for controlling systems with uncertain and varying system parameters. While simulators are useful for safely learning control policies, the reality gap remains a major challenge. To alleviate this challenge, we propose a two-stage algorithm. First, multiple control policies are learned for systems with different system parameters in a simulator. Second, for a real system, the control policies are adaptively switched using an online convex optimization algorithm based on observations. This approach is expected to reduce lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.20152","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":""},"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":"2510.20152","created_at":"2026-05-18T03:09:33.739445+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.20152v4","created_at":"2026-05-18T03:09:33.739445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.20152","created_at":"2026-05-18T03:09:33.739445+00:00"},{"alias_kind":"pith_short_12","alias_value":"TSTO6BRDXBDB","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"TSTO6BRDXBDB4ZAA","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"TSTO6BRD","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TSTO6BRDXBDB4ZAAJS64QMQ6W5","json":"https://pith.science/pith/TSTO6BRDXBDB4ZAAJS64QMQ6W5.json","graph_json":"https://pith.science/api/pith-number/TSTO6BRDXBDB4ZAAJS64QMQ6W5/graph.json","events_json":"https://pith.science/api/pith-number/TSTO6BRDXBDB4ZAAJS64QMQ6W5/events.json","paper":"https://pith.science/paper/TSTO6BRD"},"agent_actions":{"view_html":"https://pith.science/pith/TSTO6BRDXBDB4ZAAJS64QMQ6W5","download_json":"https://pith.science/pith/TSTO6BRDXBDB4ZAAJS64QMQ6W5.json","view_paper":"https://pith.science/paper/TSTO6BRD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.20152&json=true","fetch_graph":"https://pith.science/api/pith-number/TSTO6BRDXBDB4ZAAJS64QMQ6W5/graph.json","fetch_events":"https://pith.science/api/pith-number/TSTO6BRDXBDB4ZAAJS64QMQ6W5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TSTO6BRDXBDB4ZAAJS64QMQ6W5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TSTO6BRDXBDB4ZAAJS64QMQ6W5/action/storage_attestation","attest_author":"https://pith.science/pith/TSTO6BRDXBDB4ZAAJS64QMQ6W5/action/author_attestation","sign_citation":"https://pith.science/pith/TSTO6BRDXBDB4ZAAJS64QMQ6W5/action/citation_signature","submit_replication":"https://pith.science/pith/TSTO6BRDXBDB4ZAAJS64QMQ6W5/action/replication_record"}},"created_at":"2026-05-18T03:09:33.739445+00:00","updated_at":"2026-05-18T03:09:33.739445+00:00"}