{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:P4HUNZARFD5CNASISNWE63AYQN","short_pith_number":"pith:P4HUNZAR","schema_version":"1.0","canonical_sha256":"7f0f46e41128fa268248936c4f6c188351bd41ef445d3cfd1aa858d1d78ab95f","source":{"kind":"arxiv","id":"2604.04539","version":2},"attestation_state":"computed","paper":{"title":"FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"FlashSAC stabilizes off-policy RL for high-dimensional robot control by cutting gradient updates and bounding norms to limit critic errors.","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Danica Kragic, Daniel Palenicek, Donghu Kim, Florian Vogt, Hojoon Lee, I Made Aswin Nahendra, Jaegul Choo, Jan Peters, Kinam Kim, Minho Park, Sehee Min, Takuma Seno, Youngdo Lee","submitted_at":"2026-04-06T09:03:41Z","abstract_excerpt":"Reinforcement learning (RL) is a core approach for robot control when expert demonstrations are unavailable. On-policy methods such as Proximal Policy Optimization (PPO) are widely used for their stability, but their reliance on narrowly distributed on-policy data limits accurate policy evaluation in high-dimensional state and action spaces. Off-policy methods can overcome this limitation by learning from a broader state-action distribution, yet suffer from slow convergence and instability, as fitting a value function over diverse data requires many gradient updates, causing critic errors to a"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2604.04539","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-06T09:03:41Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"f94ebc986218d4761adc4446fc388da88b050823e912340b7a2eef21558e682f","abstract_canon_sha256":"ae46796841d76b3575eba32104b569b38dee8c7c75a0de345a25ac3d84abef1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:37.674882Z","signature_b64":"xmugFJTdgXJcb6ywZpjHgbuxSLPDlP/N/vTCwmAg8wTkQpH9NrTfxUZhzpjR8XncroobcUGLRITv3mazzoetBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f0f46e41128fa268248936c4f6c188351bd41ef445d3cfd1aa858d1d78ab95f","last_reissued_at":"2026-05-20T00:00:37.674180Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:37.674180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"FlashSAC stabilizes off-policy RL for high-dimensional robot control by cutting gradient updates and bounding norms to limit critic errors.","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Danica Kragic, Daniel Palenicek, Donghu Kim, Florian Vogt, Hojoon Lee, I Made Aswin Nahendra, Jaegul Choo, Jan Peters, Kinam Kim, Minho Park, Sehee Min, Takuma Seno, Youngdo Lee","submitted_at":"2026-04-06T09:03:41Z","abstract_excerpt":"Reinforcement learning (RL) is a core approach for robot control when expert demonstrations are unavailable. On-policy methods such as Proximal Policy Optimization (PPO) are widely used for their stability, but their reliance on narrowly distributed on-policy data limits accurate policy evaluation in high-dimensional state and action spaces. Off-policy methods can overcome this limitation by learning from a broader state-action distribution, yet suffer from slow convergence and instability, as fitting a value function over diverse data requires many gradient updates, causing critic errors to a"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Across over 60 tasks in 10 simulators, FlashSAC consistently outperforms PPO and strong off-policy baselines in both final performance and training efficiency, with the largest gains on high-dimensional tasks such as dexterous manipulation. In sim-to-real humanoid locomotion, FlashSAC reduces training time from hours to minutes.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That explicitly bounding weight, feature, and gradient norms will sufficiently curb critic error accumulation in high-dimensional spaces without removing the capacity needed for accurate value estimation or policy improvement.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"FlashSAC improves training speed and final performance of off-policy RL on high-dimensional robot tasks by reducing update frequency, increasing model scale, and bounding norms to limit critic error accumulation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"FlashSAC stabilizes off-policy RL for high-dimensional robot control by cutting gradient updates and bounding norms to limit critic errors.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"350de7fc0cf5087e99812e76d522f097aa206c6fc5bd272d14c2d18301905f75"},"source":{"id":"2604.04539","kind":"arxiv","version":2},"verdict":{"id":"4f1dfd44-0e81-404c-95aa-a813e0e143f9","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T17:04:49.619467Z","strongest_claim":"Across over 60 tasks in 10 simulators, FlashSAC consistently outperforms PPO and strong off-policy baselines in both final performance and training efficiency, with the largest gains on high-dimensional tasks such as dexterous manipulation. In sim-to-real humanoid locomotion, FlashSAC reduces training time from hours to minutes.","one_line_summary":"FlashSAC improves training speed and final performance of off-policy RL on high-dimensional robot tasks by reducing update frequency, increasing model scale, and bounding norms to limit critic error accumulation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That explicitly bounding weight, feature, and gradient norms will sufficiently curb critic error accumulation in high-dimensional spaces without removing the capacity needed for accurate value estimation or policy improvement.","pith_extraction_headline":"FlashSAC stabilizes off-policy RL for high-dimensional robot control by cutting gradient updates and bounding norms to limit critic errors."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.04539/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":94,"sample":[{"doi":"","year":2023,"title":"Loss of plasticity in continual deep reinforcement learning","work_id":"7ecff814-af37-405d-a70f-9c1fb4554063","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Learning dexterous in-hand manipulation.The International Journal of Robotics Research, 39(1):3–20, 2020","work_id":"d1093acb-7a4b-42e8-aa29-51fcfd4bab71","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"A brief survey of deep reinforcement learning","work_id":"3b2842ca-9c8f-4b1a-a615-22c29e63726b","ref_index":3,"cited_arxiv_id":"1708.05866","is_internal_anchor":true},{"doi":"","year":2024,"title":"Genesis: A generative and universal physics engine for robotics and beyond, December 2024","work_id":"cb89394b-6f98-44ca-8234-f0020e9373e8","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"Layer Normalization","work_id":"20a2d720-0046-4c7c-bcd6-327ec8143f69","ref_index":5,"cited_arxiv_id":"1607.06450","is_internal_anchor":true}],"resolved_work":94,"snapshot_sha256":"9ea9fa4581b88687296c237e979740aa6eb68ac1e53414cdc29123fcc43c1529","internal_anchors":18},"formal_canon":{"evidence_count":2,"snapshot_sha256":"585797ed27890a08802b5db6540d6dc87e1256c228071a6ff52fcf14ba011a2f"},"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":"2604.04539","created_at":"2026-05-20T00:00:37.674279+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.04539v2","created_at":"2026-05-20T00:00:37.674279+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.04539","created_at":"2026-05-20T00:00:37.674279+00:00"},{"alias_kind":"pith_short_12","alias_value":"P4HUNZARFD5C","created_at":"2026-05-20T00:00:37.674279+00:00"},{"alias_kind":"pith_short_16","alias_value":"P4HUNZARFD5CNASI","created_at":"2026-05-20T00:00:37.674279+00:00"},{"alias_kind":"pith_short_8","alias_value":"P4HUNZAR","created_at":"2026-05-20T00:00:37.674279+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2603.12612","citing_title":"FastDSAC: Unlocking the Potential of Maximum Entropy RL in High-Dimensional Humanoid Control","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P4HUNZARFD5CNASISNWE63AYQN","json":"https://pith.science/pith/P4HUNZARFD5CNASISNWE63AYQN.json","graph_json":"https://pith.science/api/pith-number/P4HUNZARFD5CNASISNWE63AYQN/graph.json","events_json":"https://pith.science/api/pith-number/P4HUNZARFD5CNASISNWE63AYQN/events.json","paper":"https://pith.science/paper/P4HUNZAR"},"agent_actions":{"view_html":"https://pith.science/pith/P4HUNZARFD5CNASISNWE63AYQN","download_json":"https://pith.science/pith/P4HUNZARFD5CNASISNWE63AYQN.json","view_paper":"https://pith.science/paper/P4HUNZAR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.04539&json=true","fetch_graph":"https://pith.science/api/pith-number/P4HUNZARFD5CNASISNWE63AYQN/graph.json","fetch_events":"https://pith.science/api/pith-number/P4HUNZARFD5CNASISNWE63AYQN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P4HUNZARFD5CNASISNWE63AYQN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P4HUNZARFD5CNASISNWE63AYQN/action/storage_attestation","attest_author":"https://pith.science/pith/P4HUNZARFD5CNASISNWE63AYQN/action/author_attestation","sign_citation":"https://pith.science/pith/P4HUNZARFD5CNASISNWE63AYQN/action/citation_signature","submit_replication":"https://pith.science/pith/P4HUNZARFD5CNASISNWE63AYQN/action/replication_record"}},"created_at":"2026-05-20T00:00:37.674279+00:00","updated_at":"2026-05-20T00:00:37.674279+00:00"}