{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:24TFP6W7QSWKQIVXDTX5K75QTU","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":"016ffde95fea532c04912d2ba4ad296f7600ded309ead2e6b971a7bff2060421","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-28T17:55:26Z","title_canon_sha256":"3233c6055baba31824e519b53c7bfc5f5684d04139fe4a5227372523f977d628"},"schema_version":"1.0","source":{"id":"2505.22642","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22642","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22642v3","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22642","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"pith_short_12","alias_value":"24TFP6W7QSWK","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"pith_short_16","alias_value":"24TFP6W7QSWKQIVX","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"pith_short_8","alias_value":"24TFP6W7","created_at":"2026-07-05T11:13:27Z"}],"graph_snapshots":[{"event_id":"sha256:cd5295fd3f1661a4ef22933e568792713f6d57c849f725e93467affff8e9c927","target":"graph","created_at":"2026-07-05T11:13:27Z","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/2505.22642/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has driven significant progress in robotics, but its complexity and long training times remain major bottlenecks. In this report, we introduce FastTD3, a simple, fast, and capable RL algorithm that significantly speeds up training for humanoid robots in popular suites such as HumanoidBench, IsaacLab, and MuJoCo Playground. Our recipe is remarkably simple: we train an off-policy TD3 agent with several modifications -- parallel simulation, large-batch updates, a distributional critic, and carefully tuned hyperparameters. FastTD3 solves a range of HumanoidBench tasks i","authors_text":"Carmelo Sferrazza, Haoran Geng, Michal Nauman, Pieter Abbeel, Younggyo Seo, Zhao-Heng Yin","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-28T17:55:26Z","title":"FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22642","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":"sha256:5675daf7845ab10ed63f5e16680f550850bbee3350701b46b02dae189b9f2c55","target":"record","created_at":"2026-07-05T11:13:27Z","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":"016ffde95fea532c04912d2ba4ad296f7600ded309ead2e6b971a7bff2060421","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-28T17:55:26Z","title_canon_sha256":"3233c6055baba31824e519b53c7bfc5f5684d04139fe4a5227372523f977d628"},"schema_version":"1.0","source":{"id":"2505.22642","kind":"arxiv","version":3}},"canonical_sha256":"d72657fadf84aca822b71cefd57fb09d0c39fc1600c0be45160955d787d6fcf3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d72657fadf84aca822b71cefd57fb09d0c39fc1600c0be45160955d787d6fcf3","first_computed_at":"2026-07-05T11:13:27.551900Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:27.551900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NlcdMA8fH4rFu/oIpyH5Enug/WUr58VVIYkedHyYlvvrjL9XNtIfP/ly/7rJSBqfHdxSIJF+LKJkbfwbpjt1DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:27.552389Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22642","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5675daf7845ab10ed63f5e16680f550850bbee3350701b46b02dae189b9f2c55","sha256:cd5295fd3f1661a4ef22933e568792713f6d57c849f725e93467affff8e9c927"],"state_sha256":"f95f0b73eb7c6e54a57c804d068343f9bb223f976b196cc909c6bbafd72c59ae"}