{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RRAV4LVIRA672Q5NB72WSF6ARN","short_pith_number":"pith:RRAV4LVI","schema_version":"1.0","canonical_sha256":"8c415e2ea8883dfd43ad0ff56917c08b402e6c3683f6cb817cdf56ec17ca66fe","source":{"kind":"arxiv","id":"2606.03335","version":1},"attestation_state":"computed","paper":{"title":"GPU-Parallel Multi-Task Reinforcement Learning with Demonstration Guided Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Junjie Lai, Qiwei Wu, Renjing Xu, Rui Zhang, Tao Li, Weihua Zhang, Yunrong Guo, Zhengyu Zhang","submitted_at":"2026-06-02T08:43:42Z","abstract_excerpt":"Large scale GPU-parallel reinforcement learning has changed what can be trained in robot simulation, yet most systems still optimize one specialist policy per task. We propose a construction methodology for turning structured manipulation task families into GPU-parallel multi-task RL benchmarks, and instantiate it as MT-Libero using LIBERO assets and task predicates in Isaac Lab. The resulting benchmark supports simultaneous reinforcement learning over heterogeneous task suites with parallel rendering, physics randomization, and state-input or visual-input policies. To make such training pract"},"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":"2606.03335","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-02T08:43:42Z","cross_cats_sorted":[],"title_canon_sha256":"7f382bd44fe881ddd28702d4ca146b0136edadf5cd89a231f0c5b767192ed175","abstract_canon_sha256":"4684e375f49e151bceb48159d78745141cfe8dbc4abf816cc014debdcc619b31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:55.308767Z","signature_b64":"2TPFhT6mmvsQBAYyr6gpbaO4UKxwPZm5fjM3fmZtOY3p1+7jXk8XDzTkRXH65TZUhsf3cbvoCxMxpddKKydZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c415e2ea8883dfd43ad0ff56917c08b402e6c3683f6cb817cdf56ec17ca66fe","last_reissued_at":"2026-06-03T01:05:55.308363Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:55.308363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPU-Parallel Multi-Task Reinforcement Learning with Demonstration Guided Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Junjie Lai, Qiwei Wu, Renjing Xu, Rui Zhang, Tao Li, Weihua Zhang, Yunrong Guo, Zhengyu Zhang","submitted_at":"2026-06-02T08:43:42Z","abstract_excerpt":"Large scale GPU-parallel reinforcement learning has changed what can be trained in robot simulation, yet most systems still optimize one specialist policy per task. We propose a construction methodology for turning structured manipulation task families into GPU-parallel multi-task RL benchmarks, and instantiate it as MT-Libero using LIBERO assets and task predicates in Isaac Lab. The resulting benchmark supports simultaneous reinforcement learning over heterogeneous task suites with parallel rendering, physics randomization, and state-input or visual-input policies. To make such training pract"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03335","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/2606.03335/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":"2606.03335","created_at":"2026-06-03T01:05:55.308421+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03335v1","created_at":"2026-06-03T01:05:55.308421+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03335","created_at":"2026-06-03T01:05:55.308421+00:00"},{"alias_kind":"pith_short_12","alias_value":"RRAV4LVIRA67","created_at":"2026-06-03T01:05:55.308421+00:00"},{"alias_kind":"pith_short_16","alias_value":"RRAV4LVIRA672Q5N","created_at":"2026-06-03T01:05:55.308421+00:00"},{"alias_kind":"pith_short_8","alias_value":"RRAV4LVI","created_at":"2026-06-03T01:05:55.308421+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/RRAV4LVIRA672Q5NB72WSF6ARN","json":"https://pith.science/pith/RRAV4LVIRA672Q5NB72WSF6ARN.json","graph_json":"https://pith.science/api/pith-number/RRAV4LVIRA672Q5NB72WSF6ARN/graph.json","events_json":"https://pith.science/api/pith-number/RRAV4LVIRA672Q5NB72WSF6ARN/events.json","paper":"https://pith.science/paper/RRAV4LVI"},"agent_actions":{"view_html":"https://pith.science/pith/RRAV4LVIRA672Q5NB72WSF6ARN","download_json":"https://pith.science/pith/RRAV4LVIRA672Q5NB72WSF6ARN.json","view_paper":"https://pith.science/paper/RRAV4LVI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03335&json=true","fetch_graph":"https://pith.science/api/pith-number/RRAV4LVIRA672Q5NB72WSF6ARN/graph.json","fetch_events":"https://pith.science/api/pith-number/RRAV4LVIRA672Q5NB72WSF6ARN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RRAV4LVIRA672Q5NB72WSF6ARN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RRAV4LVIRA672Q5NB72WSF6ARN/action/storage_attestation","attest_author":"https://pith.science/pith/RRAV4LVIRA672Q5NB72WSF6ARN/action/author_attestation","sign_citation":"https://pith.science/pith/RRAV4LVIRA672Q5NB72WSF6ARN/action/citation_signature","submit_replication":"https://pith.science/pith/RRAV4LVIRA672Q5NB72WSF6ARN/action/replication_record"}},"created_at":"2026-06-03T01:05:55.308421+00:00","updated_at":"2026-06-03T01:05:55.308421+00:00"}