{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:XBVD66JJ2QQI4VRV3ZHU332XLL","short_pith_number":"pith:XBVD66JJ","schema_version":"1.0","canonical_sha256":"b86a3f7929d4208e5635de4f4def575ae9a9c32387aaad28863312e9df0dc582","source":{"kind":"arxiv","id":"1305.6568","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning for the Soccer Dribbling Task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arthur Carvalho, Renato Oliveira","submitted_at":"2013-05-28T17:47:08Z","abstract_excerpt":"We propose a reinforcement learning solution to the \\emph{soccer dribbling task}, a scenario in which a soccer agent has to go from the beginning to the end of a region keeping possession of the ball, as an adversary attempts to gain possession. While the adversary uses a stationary policy, the dribbler learns the best action to take at each decision point. After defining meaningful variables to represent the state space, and high-level macro-actions to incorporate domain knowledge, we describe our application of the reinforcement learning algorithm \\emph{Sarsa} with CMAC for function approxim"},"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":"1305.6568","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-05-28T17:47:08Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"97991dc0cd2a7a95ef6a49623a25cf652b209b58f3ecb6f252fe3cd735c9cdb1","abstract_canon_sha256":"cc538f891a1675892abb6fcc5cc1533c6fa1005ec765b53f421fadd8c19ee22c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:24:40.409629Z","signature_b64":"z3+q1rsYIWDyqXrjn5qxjczGfC9t0T/xGttI+WT7tUiMeDHfktq2o1i1EaTJynEf7oB+JRdcF1gKPiCBNfuYBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b86a3f7929d4208e5635de4f4def575ae9a9c32387aaad28863312e9df0dc582","last_reissued_at":"2026-05-18T03:24:40.409067Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:24:40.409067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning for the Soccer Dribbling Task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arthur Carvalho, Renato Oliveira","submitted_at":"2013-05-28T17:47:08Z","abstract_excerpt":"We propose a reinforcement learning solution to the \\emph{soccer dribbling task}, a scenario in which a soccer agent has to go from the beginning to the end of a region keeping possession of the ball, as an adversary attempts to gain possession. While the adversary uses a stationary policy, the dribbler learns the best action to take at each decision point. After defining meaningful variables to represent the state space, and high-level macro-actions to incorporate domain knowledge, we describe our application of the reinforcement learning algorithm \\emph{Sarsa} with CMAC for function approxim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1305.6568","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":""},"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":"1305.6568","created_at":"2026-05-18T03:24:40.409154+00:00"},{"alias_kind":"arxiv_version","alias_value":"1305.6568v1","created_at":"2026-05-18T03:24:40.409154+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1305.6568","created_at":"2026-05-18T03:24:40.409154+00:00"},{"alias_kind":"pith_short_12","alias_value":"XBVD66JJ2QQI","created_at":"2026-05-18T12:28:06.772260+00:00"},{"alias_kind":"pith_short_16","alias_value":"XBVD66JJ2QQI4VRV","created_at":"2026-05-18T12:28:06.772260+00:00"},{"alias_kind":"pith_short_8","alias_value":"XBVD66JJ","created_at":"2026-05-18T12:28:06.772260+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/XBVD66JJ2QQI4VRV3ZHU332XLL","json":"https://pith.science/pith/XBVD66JJ2QQI4VRV3ZHU332XLL.json","graph_json":"https://pith.science/api/pith-number/XBVD66JJ2QQI4VRV3ZHU332XLL/graph.json","events_json":"https://pith.science/api/pith-number/XBVD66JJ2QQI4VRV3ZHU332XLL/events.json","paper":"https://pith.science/paper/XBVD66JJ"},"agent_actions":{"view_html":"https://pith.science/pith/XBVD66JJ2QQI4VRV3ZHU332XLL","download_json":"https://pith.science/pith/XBVD66JJ2QQI4VRV3ZHU332XLL.json","view_paper":"https://pith.science/paper/XBVD66JJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1305.6568&json=true","fetch_graph":"https://pith.science/api/pith-number/XBVD66JJ2QQI4VRV3ZHU332XLL/graph.json","fetch_events":"https://pith.science/api/pith-number/XBVD66JJ2QQI4VRV3ZHU332XLL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XBVD66JJ2QQI4VRV3ZHU332XLL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XBVD66JJ2QQI4VRV3ZHU332XLL/action/storage_attestation","attest_author":"https://pith.science/pith/XBVD66JJ2QQI4VRV3ZHU332XLL/action/author_attestation","sign_citation":"https://pith.science/pith/XBVD66JJ2QQI4VRV3ZHU332XLL/action/citation_signature","submit_replication":"https://pith.science/pith/XBVD66JJ2QQI4VRV3ZHU332XLL/action/replication_record"}},"created_at":"2026-05-18T03:24:40.409154+00:00","updated_at":"2026-05-18T03:24:40.409154+00:00"}