{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KKGGE6Z7TJL37CGBCPS5UKEDJH","short_pith_number":"pith:KKGGE6Z7","schema_version":"1.0","canonical_sha256":"528c627b3f9a57bf88c113e5da288349e723f5fabffc3af8ef3e3b027c59f5c5","source":{"kind":"arxiv","id":"2405.02425","version":1},"attestation_state":"computed","paper":{"title":"Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Arunkumar Byravan, Ben Moran, Dhruva Tirumala, Francesco Nori, Guy Lever, Jan Humplik, Kushal Patel, Leonard Hasenclever, Markus Wulfmeier, Marlon Gwira, Martin Riedmiller, Nathan Batchelor, Neil Sreendra, Nicolas Heess, Sandy Huang, Tuomas Haarnoja","submitted_at":"2024-05-03T18:41:13Z","abstract_excerpt":"We apply multi-agent deep reinforcement learning (RL) to train end-to-end robot soccer policies with fully onboard computation and sensing via egocentric RGB vision. This setting reflects many challenges of real-world robotics, including active perception, agile full-body control, and long-horizon planning in a dynamic, partially-observable, multi-agent domain. We rely on large-scale, simulation-based data generation to obtain complex behaviors from egocentric vision which can be successfully transferred to physical robots using low-cost sensors. To achieve adequate visual realism, our simulat"},"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":"2405.02425","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-05-03T18:41:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8c521d0523ae39d06ee94fcf874c261bc91db400fa5e89030a4c35fa4cec2add","abstract_canon_sha256":"deea65d2af105805aaf6b778e90e26eb43f02704966d2d789e3a6b7d97216987"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:15.495026Z","signature_b64":"JvMOxetzMMwXZW9PAGGqr2uzFoRmY3nfnMzD+OtUYK8zRP4pFPsRDeoHB/s9q0SIYdhT8WQhodJmMIRZcbL2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"528c627b3f9a57bf88c113e5da288349e723f5fabffc3af8ef3e3b027c59f5c5","last_reissued_at":"2026-07-05T08:15:15.494527Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:15.494527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Arunkumar Byravan, Ben Moran, Dhruva Tirumala, Francesco Nori, Guy Lever, Jan Humplik, Kushal Patel, Leonard Hasenclever, Markus Wulfmeier, Marlon Gwira, Martin Riedmiller, Nathan Batchelor, Neil Sreendra, Nicolas Heess, Sandy Huang, Tuomas Haarnoja","submitted_at":"2024-05-03T18:41:13Z","abstract_excerpt":"We apply multi-agent deep reinforcement learning (RL) to train end-to-end robot soccer policies with fully onboard computation and sensing via egocentric RGB vision. This setting reflects many challenges of real-world robotics, including active perception, agile full-body control, and long-horizon planning in a dynamic, partially-observable, multi-agent domain. We rely on large-scale, simulation-based data generation to obtain complex behaviors from egocentric vision which can be successfully transferred to physical robots using low-cost sensors. To achieve adequate visual realism, our simulat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02425","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/2405.02425/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":"2405.02425","created_at":"2026-07-05T08:15:15.494593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.02425v1","created_at":"2026-07-05T08:15:15.494593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02425","created_at":"2026-07-05T08:15:15.494593+00:00"},{"alias_kind":"pith_short_12","alias_value":"KKGGE6Z7TJL3","created_at":"2026-07-05T08:15:15.494593+00:00"},{"alias_kind":"pith_short_16","alias_value":"KKGGE6Z7TJL37CGB","created_at":"2026-07-05T08:15:15.494593+00:00"},{"alias_kind":"pith_short_8","alias_value":"KKGGE6Z7","created_at":"2026-07-05T08:15:15.494593+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.04681","citing_title":"Perceiving and Acting in First-Person: A Dataset and Benchmark for Egocentric Human-Object-Human Interactions","ref_index":113,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KKGGE6Z7TJL37CGBCPS5UKEDJH","json":"https://pith.science/pith/KKGGE6Z7TJL37CGBCPS5UKEDJH.json","graph_json":"https://pith.science/api/pith-number/KKGGE6Z7TJL37CGBCPS5UKEDJH/graph.json","events_json":"https://pith.science/api/pith-number/KKGGE6Z7TJL37CGBCPS5UKEDJH/events.json","paper":"https://pith.science/paper/KKGGE6Z7"},"agent_actions":{"view_html":"https://pith.science/pith/KKGGE6Z7TJL37CGBCPS5UKEDJH","download_json":"https://pith.science/pith/KKGGE6Z7TJL37CGBCPS5UKEDJH.json","view_paper":"https://pith.science/paper/KKGGE6Z7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.02425&json=true","fetch_graph":"https://pith.science/api/pith-number/KKGGE6Z7TJL37CGBCPS5UKEDJH/graph.json","fetch_events":"https://pith.science/api/pith-number/KKGGE6Z7TJL37CGBCPS5UKEDJH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KKGGE6Z7TJL37CGBCPS5UKEDJH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KKGGE6Z7TJL37CGBCPS5UKEDJH/action/storage_attestation","attest_author":"https://pith.science/pith/KKGGE6Z7TJL37CGBCPS5UKEDJH/action/author_attestation","sign_citation":"https://pith.science/pith/KKGGE6Z7TJL37CGBCPS5UKEDJH/action/citation_signature","submit_replication":"https://pith.science/pith/KKGGE6Z7TJL37CGBCPS5UKEDJH/action/replication_record"}},"created_at":"2026-07-05T08:15:15.494593+00:00","updated_at":"2026-07-05T08:15:15.494593+00:00"}