{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7HRRBD7VMHV6SW4TDHBDYOF7AQ","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":"48d23826ccc7d85e37f10f9cb0661613f5901e2aa33e222cda88ed72e2edc808","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2020-04-29T16:14:30Z","title_canon_sha256":"af3e628c13bdc3baf1e4434f7a17d14bd55838e794b3b2f7ad9f9af8b31f3046"},"schema_version":"1.0","source":{"id":"2004.14288","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14288","created_at":"2026-07-05T01:19:27Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14288v3","created_at":"2026-07-05T01:19:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14288","created_at":"2026-07-05T01:19:27Z"},{"alias_kind":"pith_short_12","alias_value":"7HRRBD7VMHV6","created_at":"2026-07-05T01:19:27Z"},{"alias_kind":"pith_short_16","alias_value":"7HRRBD7VMHV6SW4T","created_at":"2026-07-05T01:19:27Z"},{"alias_kind":"pith_short_8","alias_value":"7HRRBD7V","created_at":"2026-07-05T01:19:27Z"}],"graph_snapshots":[{"event_id":"sha256:792f71e086e2931e802f2990fc93123b92936c8e2aebb9516fa1900239fa5264","target":"graph","created_at":"2026-07-05T01:19:27Z","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/2004.14288/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) and its integration with deep learning have achieved impressive performance in various robotic control tasks, ranging from motion planning and navigation to end-to-end visual manipulation. However, stability is not guaranteed in model-free RL by solely using data. From a control-theoretic perspective, stability is the most important property for any control system, since it is closely related to safety, robustness, and reliability of robotic systems. In this paper, we propose an actor-critic RL framework for control which can guarantee closed-loop stability by emplo","authors_text":"Jun Wang, Lixian Zhang, Minghao Han, Wei Pan","cross_cats":["cs.LG","cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2020-04-29T16:14:30Z","title":"Actor-Critic Reinforcement Learning for Control with Stability Guarantee"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14288","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:c3438304e0db159b098b1dc1c980a88a44ec57fc8926f6483d587082569cb78f","target":"record","created_at":"2026-07-05T01:19:27Z","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":"48d23826ccc7d85e37f10f9cb0661613f5901e2aa33e222cda88ed72e2edc808","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2020-04-29T16:14:30Z","title_canon_sha256":"af3e628c13bdc3baf1e4434f7a17d14bd55838e794b3b2f7ad9f9af8b31f3046"},"schema_version":"1.0","source":{"id":"2004.14288","kind":"arxiv","version":3}},"canonical_sha256":"f9e3108ff561ebe95b9319c23c38bf040ff4fe27492d440abe74be07f4160810","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9e3108ff561ebe95b9319c23c38bf040ff4fe27492d440abe74be07f4160810","first_computed_at":"2026-07-05T01:19:27.174105Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:19:27.174105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n1XK+k30Ae6EUzmQz3NEBNO1f3MIXDazhXrVnfBeLqmtctiD7WPcPNi5U/XFx8u2I/t+wgAMHrwaEt2oTXZaAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:19:27.174671Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.14288","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3438304e0db159b098b1dc1c980a88a44ec57fc8926f6483d587082569cb78f","sha256:792f71e086e2931e802f2990fc93123b92936c8e2aebb9516fa1900239fa5264"],"state_sha256":"a737b05c989453b92125895934aab4005141450aa1340635b7e28aa5cb05afc4"}