{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Z77DXAJETVYGRTSBXH7T4R6PW3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4c18e5e95a274bd776805398c17ec09421b016ef52bcda0e6e784b10be748047","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-12T16:25:10Z","title_canon_sha256":"d4398b0fbd04be650e6744dc2163b72d44f1655a0110304e990af75b561c4d3e"},"schema_version":"1.0","source":{"id":"2412.09417","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09417","created_at":"2026-07-05T10:26:11Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09417v2","created_at":"2026-07-05T10:26:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09417","created_at":"2026-07-05T10:26:11Z"},{"alias_kind":"pith_short_12","alias_value":"Z77DXAJETVYG","created_at":"2026-07-05T10:26:11Z"},{"alias_kind":"pith_short_16","alias_value":"Z77DXAJETVYGRTSB","created_at":"2026-07-05T10:26:11Z"},{"alias_kind":"pith_short_8","alias_value":"Z77DXAJE","created_at":"2026-07-05T10:26:11Z"}],"graph_snapshots":[{"event_id":"sha256:eb41eb6c15ca913beae160c0d0679ca491585059b3e2386b1ccb146a5a950f2b","target":"graph","created_at":"2026-07-05T10:26:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.09417/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-12T16:25:10Z","title":"Reinforcement Learning Within the Classical Robotics Stack: A Case Study in Robot Soccer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09417","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:dc4036cf237d9345cdb187c31255fa236632fbc9828a9335afbc974c9d7e1ec0","target":"record","created_at":"2026-07-05T10:26:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4c18e5e95a274bd776805398c17ec09421b016ef52bcda0e6e784b10be748047","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-12T16:25:10Z","title_canon_sha256":"d4398b0fbd04be650e6744dc2163b72d44f1655a0110304e990af75b561c4d3e"},"schema_version":"1.0","source":{"id":"2412.09417","kind":"arxiv","version":2}},"canonical_sha256":"cffe3b81249d7068ce41b9ff3e47cfb6cd7832d58a5138d65019f4cd80adc5d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cffe3b81249d7068ce41b9ff3e47cfb6cd7832d58a5138d65019f4cd80adc5d7","first_computed_at":"2026-07-05T10:26:11.676608Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:26:11.676608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B9/YCHwYGs4mIxzo+USt2E0U/33XnBvLHt6y6LkDZ0BIVya2ApJmWvcrhPKIdzfH/6GDgGINhMsTocEHHc3BAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:26:11.677179Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.09417","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc4036cf237d9345cdb187c31255fa236632fbc9828a9335afbc974c9d7e1ec0","sha256:eb41eb6c15ca913beae160c0d0679ca491585059b3e2386b1ccb146a5a950f2b"],"state_sha256":"17997fd0b6902cad10662f26211ac591af988212fa4ec48afb6fa37e26f6c456"}