{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PLYFZSCDT44X5CF26S47LLFWVY","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":"0d3beda3dc9d41bfb045a60512a37134bf3f816dada945dc9e9db08662ad681a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-03-01T22:16:27Z","title_canon_sha256":"c6008b650205af21d987fb988f5d548ff52a34c29d0401fa34a0d9579577740b"},"schema_version":"1.0","source":{"id":"2603.01302","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.01302","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"2603.01302v2","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.01302","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"PLYFZSCDT44X","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"pith_short_16","alias_value":"PLYFZSCDT44X5CF2","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"pith_short_8","alias_value":"PLYFZSCD","created_at":"2026-06-02T01:03:44Z"}],"graph_snapshots":[{"event_id":"sha256:f8869d02ef9a800549d1e9a9ed63adebd00456102b4ebfb32e12ea04a164fea9","target":"graph","created_at":"2026-06-02T01:03:44Z","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/2603.01302/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning in discrete-continuous hybrid action spaces presents fundamental challenges for robotic manipulation, where high-level task decisions and low-level joint-space execution must be jointly optimized. Existing approaches either discretize continuous components or relax discrete choices into continuous approximations, which suffer from scalability limitations and training instability in high-dimensional action spaces and under domain randomization. In this paper, we propose Hybrid TD3, an extension of Twin Delayed Deep Deterministic Policy Gradient (TD3) that natively handles","authors_text":"Nak Young Chong, Thanh Nguyen Canh, Thanh-Tuan Tran, Xiem HoangVan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-03-01T22:16:27Z","title":"Hybrid TD3: Overestimation Bias Analysis and Stable Policy Optimization for Hybrid Action Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.01302","kind":"arxiv","version":2},"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:b47e3157db3cfa3f5dfe927068df63cd4a1ecfa971d606bc1e9bd699dba41f02","target":"record","created_at":"2026-06-02T01:03:44Z","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":"0d3beda3dc9d41bfb045a60512a37134bf3f816dada945dc9e9db08662ad681a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-03-01T22:16:27Z","title_canon_sha256":"c6008b650205af21d987fb988f5d548ff52a34c29d0401fa34a0d9579577740b"},"schema_version":"1.0","source":{"id":"2603.01302","kind":"arxiv","version":2}},"canonical_sha256":"7af05cc8439f397e88baf4b9f5acb6ae19e852138c5196191439fb4c7e232d47","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7af05cc8439f397e88baf4b9f5acb6ae19e852138c5196191439fb4c7e232d47","first_computed_at":"2026-06-02T01:03:44.419562Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:44.419562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BHDmCfkN6c0a3YTF2sUs6Vn04MvDCXIZN2NzRDg5MO6EQ0APB/riBFwQ2jbRZgpmTw7X4CSfZPBvNHNPmA3OBQ==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:44.420075Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.01302","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b47e3157db3cfa3f5dfe927068df63cd4a1ecfa971d606bc1e9bd699dba41f02","sha256:f8869d02ef9a800549d1e9a9ed63adebd00456102b4ebfb32e12ea04a164fea9"],"state_sha256":"09d4c062541c673f577f99dcf898697006cc2fb0e0e866ca90cac59bb85baa71"}