{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z77DXAJETVYGRTSBXH7T4R6PW3","short_pith_number":"pith:Z77DXAJE","schema_version":"1.0","canonical_sha256":"cffe3b81249d7068ce41b9ff3e47cfb6cd7832d58a5138d65019f4cd80adc5d7","source":{"kind":"arxiv","id":"2412.09417","version":2},"attestation_state":"computed","paper":{"title":"Reinforcement Learning Within the Classical Robotics Stack: A Case Study in Robot Soccer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Abhinav Narayan Harish, Adam Labiosa, Benjamin Hong, Chen Li, Geethika Hemkumar, Josh Kelle, Josiah P. Hanna, Peter Stone, Siddhant Agarwal, William Cong, Yuhao Li, Zhihan Wang, Zisen Shao","submitted_at":"2024-12-12T16:25:10Z","abstract_excerpt":"Robot decision-making in partially observable, real-time, dynamic, and multi-agent environments remains a difficult and unsolved challenge. Model-free reinforcement learning (RL) is a promising approach to learning decision-making in such domains, however, end-to-end RL in complex environments is often intractable. To address this challenge in the RoboCup Standard Platform League (SPL) domain, we developed a novel architecture integrating RL within a classical robotics stack, while employing a multi-fidelity sim2real approach and decomposing behavior into learned sub-behaviors with heuristic s"},"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":"2412.09417","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-12T16:25:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d4398b0fbd04be650e6744dc2163b72d44f1655a0110304e990af75b561c4d3e","abstract_canon_sha256":"4c18e5e95a274bd776805398c17ec09421b016ef52bcda0e6e784b10be748047"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:11.677179Z","signature_b64":"B9/YCHwYGs4mIxzo+USt2E0U/33XnBvLHt6y6LkDZ0BIVya2ApJmWvcrhPKIdzfH/6GDgGINhMsTocEHHc3BAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cffe3b81249d7068ce41b9ff3e47cfb6cd7832d58a5138d65019f4cd80adc5d7","last_reissued_at":"2026-07-05T10:26:11.676608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:11.676608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning Within the Classical Robotics Stack: A Case Study in Robot Soccer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Abhinav Narayan Harish, Adam Labiosa, Benjamin Hong, Chen Li, Geethika Hemkumar, Josh Kelle, Josiah P. Hanna, Peter Stone, Siddhant Agarwal, William Cong, Yuhao Li, Zhihan Wang, Zisen Shao","submitted_at":"2024-12-12T16:25:10Z","abstract_excerpt":"Robot decision-making in partially observable, real-time, dynamic, and multi-agent environments remains a difficult and unsolved challenge. Model-free reinforcement learning (RL) is a promising approach to learning decision-making in such domains, however, end-to-end RL in complex environments is often intractable. To address this challenge in the RoboCup Standard Platform League (SPL) domain, we developed a novel architecture integrating RL within a classical robotics stack, while employing a multi-fidelity sim2real approach and decomposing behavior into learned sub-behaviors with heuristic s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09417","kind":"arxiv","version":2},"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/2412.09417/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":"2412.09417","created_at":"2026-07-05T10:26:11.676674+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09417v2","created_at":"2026-07-05T10:26:11.676674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09417","created_at":"2026-07-05T10:26:11.676674+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z77DXAJETVYG","created_at":"2026-07-05T10:26:11.676674+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z77DXAJETVYGRTSB","created_at":"2026-07-05T10:26:11.676674+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z77DXAJE","created_at":"2026-07-05T10:26:11.676674+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.13834","citing_title":"Toward Real-World Cooperative and Competitive Soccer with Quadrupedal Robot Teams","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z77DXAJETVYGRTSBXH7T4R6PW3","json":"https://pith.science/pith/Z77DXAJETVYGRTSBXH7T4R6PW3.json","graph_json":"https://pith.science/api/pith-number/Z77DXAJETVYGRTSBXH7T4R6PW3/graph.json","events_json":"https://pith.science/api/pith-number/Z77DXAJETVYGRTSBXH7T4R6PW3/events.json","paper":"https://pith.science/paper/Z77DXAJE"},"agent_actions":{"view_html":"https://pith.science/pith/Z77DXAJETVYGRTSBXH7T4R6PW3","download_json":"https://pith.science/pith/Z77DXAJETVYGRTSBXH7T4R6PW3.json","view_paper":"https://pith.science/paper/Z77DXAJE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09417&json=true","fetch_graph":"https://pith.science/api/pith-number/Z77DXAJETVYGRTSBXH7T4R6PW3/graph.json","fetch_events":"https://pith.science/api/pith-number/Z77DXAJETVYGRTSBXH7T4R6PW3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z77DXAJETVYGRTSBXH7T4R6PW3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z77DXAJETVYGRTSBXH7T4R6PW3/action/storage_attestation","attest_author":"https://pith.science/pith/Z77DXAJETVYGRTSBXH7T4R6PW3/action/author_attestation","sign_citation":"https://pith.science/pith/Z77DXAJETVYGRTSBXH7T4R6PW3/action/citation_signature","submit_replication":"https://pith.science/pith/Z77DXAJETVYGRTSBXH7T4R6PW3/action/replication_record"}},"created_at":"2026-07-05T10:26:11.676674+00:00","updated_at":"2026-07-05T10:26:11.676674+00:00"}