{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CDLA3MQOO6R6XNRV57W5TTCUL5","short_pith_number":"pith:CDLA3MQO","schema_version":"1.0","canonical_sha256":"10d60db20e77a3ebb635efedd9cc545f6e759a583aea825996d6312cdfbd2233","source":{"kind":"arxiv","id":"2109.11978","version":3},"attestation_state":"computed","paper":{"title":"Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"David Hoeller, Marco Hutter, Nikita Rudin, Philipp Reist","submitted_at":"2021-09-24T14:04:19Z","abstract_excerpt":"In this work, we present and study a training set-up that achieves fast policy generation for real-world robotic tasks by using massive parallelism on a single workstation GPU. We analyze and discuss the impact of different training algorithm components in the massively parallel regime on the final policy performance and training times. In addition, we present a novel game-inspired curriculum that is well suited for training with thousands of simulated robots in parallel. We evaluate the approach by training the quadrupedal robot ANYmal to walk on challenging terrain. The parallel approach all"},"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":"2109.11978","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-09-24T14:04:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5ac3985e7fcb5d168ffa7ff51666870577b1185d15cee2effa0ecfee38462732","abstract_canon_sha256":"d59545b12bf8ccff2fa98281af110b5da5c58c42284317a94baa4fb0b11199d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:49:42.563612Z","signature_b64":"tklbu+/qmOqcAH74/STPahF1q36l+Sh/ZPweQ/U2mD6vN8jBVeTrXxxUGxraD2xLVM8W+uWXR6pcbWJ6PmDgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10d60db20e77a3ebb635efedd9cc545f6e759a583aea825996d6312cdfbd2233","last_reissued_at":"2026-07-05T04:49:42.563142Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:49:42.563142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"David Hoeller, Marco Hutter, Nikita Rudin, Philipp Reist","submitted_at":"2021-09-24T14:04:19Z","abstract_excerpt":"In this work, we present and study a training set-up that achieves fast policy generation for real-world robotic tasks by using massive parallelism on a single workstation GPU. We analyze and discuss the impact of different training algorithm components in the massively parallel regime on the final policy performance and training times. In addition, we present a novel game-inspired curriculum that is well suited for training with thousands of simulated robots in parallel. We evaluate the approach by training the quadrupedal robot ANYmal to walk on challenging terrain. The parallel approach all"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.11978","kind":"arxiv","version":3},"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/2109.11978/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":"2109.11978","created_at":"2026-07-05T04:49:42.563202+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.11978v3","created_at":"2026-07-05T04:49:42.563202+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.11978","created_at":"2026-07-05T04:49:42.563202+00:00"},{"alias_kind":"pith_short_12","alias_value":"CDLA3MQOO6R6","created_at":"2026-07-05T04:49:42.563202+00:00"},{"alias_kind":"pith_short_16","alias_value":"CDLA3MQOO6R6XNRV","created_at":"2026-07-05T04:49:42.563202+00:00"},{"alias_kind":"pith_short_8","alias_value":"CDLA3MQO","created_at":"2026-07-05T04:49:42.563202+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19333","citing_title":"Do as I Do: Dexterous Manipulation Data from Everyday Human Videos","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08564","citing_title":"Real-IKEA: Physical Fidelity is the Prerequisite for Robust Manipulation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28237","citing_title":"Unleashing Infinite Motion: Scaling Expressive Quadrupedal Motion via Generative Video Priors","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26478","citing_title":"Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradient","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09439","citing_title":"Tracking the Effective Surface Area of Non-Convex Satellites","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2510.03599","citing_title":"Learning to Act Through Contact: A Unified View of Multi-Task Robot Learning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2512.19576","citing_title":"LeLaR: The First In-Orbit Demonstration of an AI-Based Satellite Attitude Controller","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03846","citing_title":"SigLoMa: Learning Open-World Quadrupedal Loco-Manipulation from Ego-Centric Vision","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05394","citing_title":"Neural Assistive Impulses: Synthesizing Exaggerated Motions for Physics-based Characters","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CDLA3MQOO6R6XNRV57W5TTCUL5","json":"https://pith.science/pith/CDLA3MQOO6R6XNRV57W5TTCUL5.json","graph_json":"https://pith.science/api/pith-number/CDLA3MQOO6R6XNRV57W5TTCUL5/graph.json","events_json":"https://pith.science/api/pith-number/CDLA3MQOO6R6XNRV57W5TTCUL5/events.json","paper":"https://pith.science/paper/CDLA3MQO"},"agent_actions":{"view_html":"https://pith.science/pith/CDLA3MQOO6R6XNRV57W5TTCUL5","download_json":"https://pith.science/pith/CDLA3MQOO6R6XNRV57W5TTCUL5.json","view_paper":"https://pith.science/paper/CDLA3MQO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.11978&json=true","fetch_graph":"https://pith.science/api/pith-number/CDLA3MQOO6R6XNRV57W5TTCUL5/graph.json","fetch_events":"https://pith.science/api/pith-number/CDLA3MQOO6R6XNRV57W5TTCUL5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CDLA3MQOO6R6XNRV57W5TTCUL5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CDLA3MQOO6R6XNRV57W5TTCUL5/action/storage_attestation","attest_author":"https://pith.science/pith/CDLA3MQOO6R6XNRV57W5TTCUL5/action/author_attestation","sign_citation":"https://pith.science/pith/CDLA3MQOO6R6XNRV57W5TTCUL5/action/citation_signature","submit_replication":"https://pith.science/pith/CDLA3MQOO6R6XNRV57W5TTCUL5/action/replication_record"}},"created_at":"2026-07-05T04:49:42.563202+00:00","updated_at":"2026-07-05T04:49:42.563202+00:00"}