{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EAO5OBV2UJJLC3TFX24SACFNJ2","short_pith_number":"pith:EAO5OBV2","schema_version":"1.0","canonical_sha256":"201dd706baa252b16e65beb92008ad4eab0acaedf8e9ae5632d9c6ff355143e1","source":{"kind":"arxiv","id":"2606.31691","version":1},"attestation_state":"computed","paper":{"title":"FastDSAC: Enhancing Policy Plasticity via Constrained Exploration for Scalable Humanoid Locomotion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Guanchen Lu, Guofa Li, Jie Li, Jingliang Duan, Letian Tao, Yajuan Dun, Yi Zhou","submitted_at":"2026-06-30T14:04:26Z","abstract_excerpt":"Scalable reinforcement learning has popularized high-throughput sampling architectures, which significantly compresses the training time for off-policy methods in robotic locomotion. However, the rapid increase of data volume and update frequency undermines the stability of value-based methods and diminishes the plasticity of policy networks. To address these challenges, this work presents FastDSAC, a fast and high-performance variant of the Distributional Actor-Critic algorithm designed for parallel sampling scenarios. Specifically, we introduce a truncated Gaussian distribution to approximat"},"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":"2606.31691","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-30T14:04:26Z","cross_cats_sorted":[],"title_canon_sha256":"c2d767b44f54e928feb41ff07c1ea4dc3cdcdddc0d2a128c0800530c60c2c1b3","abstract_canon_sha256":"3886860923c8f8d9ae567d8924e2794573ebe04a7e5aad0905b980c130366be3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:18:11.798075Z","signature_b64":"yaDXD5qQnThr1WaFLEZYN1VGF3y+Z6ktoedlZjDmXR/TQfHD5rYPq7+jt4/1MjjpotX7JvAsio/LrM9Fih9UDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"201dd706baa252b16e65beb92008ad4eab0acaedf8e9ae5632d9c6ff355143e1","last_reissued_at":"2026-07-01T01:18:11.797662Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:18:11.797662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FastDSAC: Enhancing Policy Plasticity via Constrained Exploration for Scalable Humanoid Locomotion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Guanchen Lu, Guofa Li, Jie Li, Jingliang Duan, Letian Tao, Yajuan Dun, Yi Zhou","submitted_at":"2026-06-30T14:04:26Z","abstract_excerpt":"Scalable reinforcement learning has popularized high-throughput sampling architectures, which significantly compresses the training time for off-policy methods in robotic locomotion. However, the rapid increase of data volume and update frequency undermines the stability of value-based methods and diminishes the plasticity of policy networks. To address these challenges, this work presents FastDSAC, a fast and high-performance variant of the Distributional Actor-Critic algorithm designed for parallel sampling scenarios. Specifically, we introduce a truncated Gaussian distribution to approximat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31691","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.31691/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2606.31691","created_at":"2026-07-01T01:18:11.797716+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31691v1","created_at":"2026-07-01T01:18:11.797716+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31691","created_at":"2026-07-01T01:18:11.797716+00:00"},{"alias_kind":"pith_short_12","alias_value":"EAO5OBV2UJJL","created_at":"2026-07-01T01:18:11.797716+00:00"},{"alias_kind":"pith_short_16","alias_value":"EAO5OBV2UJJLC3TF","created_at":"2026-07-01T01:18:11.797716+00:00"},{"alias_kind":"pith_short_8","alias_value":"EAO5OBV2","created_at":"2026-07-01T01:18:11.797716+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/EAO5OBV2UJJLC3TFX24SACFNJ2","json":"https://pith.science/pith/EAO5OBV2UJJLC3TFX24SACFNJ2.json","graph_json":"https://pith.science/api/pith-number/EAO5OBV2UJJLC3TFX24SACFNJ2/graph.json","events_json":"https://pith.science/api/pith-number/EAO5OBV2UJJLC3TFX24SACFNJ2/events.json","paper":"https://pith.science/paper/EAO5OBV2"},"agent_actions":{"view_html":"https://pith.science/pith/EAO5OBV2UJJLC3TFX24SACFNJ2","download_json":"https://pith.science/pith/EAO5OBV2UJJLC3TFX24SACFNJ2.json","view_paper":"https://pith.science/paper/EAO5OBV2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31691&json=true","fetch_graph":"https://pith.science/api/pith-number/EAO5OBV2UJJLC3TFX24SACFNJ2/graph.json","fetch_events":"https://pith.science/api/pith-number/EAO5OBV2UJJLC3TFX24SACFNJ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EAO5OBV2UJJLC3TFX24SACFNJ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EAO5OBV2UJJLC3TFX24SACFNJ2/action/storage_attestation","attest_author":"https://pith.science/pith/EAO5OBV2UJJLC3TFX24SACFNJ2/action/author_attestation","sign_citation":"https://pith.science/pith/EAO5OBV2UJJLC3TFX24SACFNJ2/action/citation_signature","submit_replication":"https://pith.science/pith/EAO5OBV2UJJLC3TFX24SACFNJ2/action/replication_record"}},"created_at":"2026-07-01T01:18:11.797716+00:00","updated_at":"2026-07-01T01:18:11.797716+00:00"}