{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:XBVD66JJ2QQI4VRV3ZHU332XLL","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":"cc538f891a1675892abb6fcc5cc1533c6fa1005ec765b53f421fadd8c19ee22c","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-05-28T17:47:08Z","title_canon_sha256":"97991dc0cd2a7a95ef6a49623a25cf652b209b58f3ecb6f252fe3cd735c9cdb1"},"schema_version":"1.0","source":{"id":"1305.6568","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1305.6568","created_at":"2026-05-18T03:24:40Z"},{"alias_kind":"arxiv_version","alias_value":"1305.6568v1","created_at":"2026-05-18T03:24:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1305.6568","created_at":"2026-05-18T03:24:40Z"},{"alias_kind":"pith_short_12","alias_value":"XBVD66JJ2QQI","created_at":"2026-05-18T12:28:06Z"},{"alias_kind":"pith_short_16","alias_value":"XBVD66JJ2QQI4VRV","created_at":"2026-05-18T12:28:06Z"},{"alias_kind":"pith_short_8","alias_value":"XBVD66JJ","created_at":"2026-05-18T12:28:06Z"}],"graph_snapshots":[{"event_id":"sha256:97069056fd60f8be1a8207b829f04b2c2d916d0d6998a197821cb8963bbad23b","target":"graph","created_at":"2026-05-18T03:24:40Z","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"},"paper":{"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","authors_text":"Arthur Carvalho, Renato Oliveira","cross_cats":["cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-05-28T17:47:08Z","title":"Reinforcement Learning for the Soccer Dribbling Task"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1305.6568","kind":"arxiv","version":1},"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":"sha256:26d5b3561d687bdce5b95c78171dbc1223b4634d5c3969097d73f4553192e55f","target":"record","created_at":"2026-05-18T03:24:40Z","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":"cc538f891a1675892abb6fcc5cc1533c6fa1005ec765b53f421fadd8c19ee22c","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-05-28T17:47:08Z","title_canon_sha256":"97991dc0cd2a7a95ef6a49623a25cf652b209b58f3ecb6f252fe3cd735c9cdb1"},"schema_version":"1.0","source":{"id":"1305.6568","kind":"arxiv","version":1}},"canonical_sha256":"b86a3f7929d4208e5635de4f4def575ae9a9c32387aaad28863312e9df0dc582","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b86a3f7929d4208e5635de4f4def575ae9a9c32387aaad28863312e9df0dc582","first_computed_at":"2026-05-18T03:24:40.409067Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:24:40.409067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z3+q1rsYIWDyqXrjn5qxjczGfC9t0T/xGttI+WT7tUiMeDHfktq2o1i1EaTJynEf7oB+JRdcF1gKPiCBNfuYBA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:24:40.409629Z","signed_message":"canonical_sha256_bytes"},"source_id":"1305.6568","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26d5b3561d687bdce5b95c78171dbc1223b4634d5c3969097d73f4553192e55f","sha256:97069056fd60f8be1a8207b829f04b2c2d916d0d6998a197821cb8963bbad23b"],"state_sha256":"47d5e0033562afeaf8cfcde68838963939dbb66739c2f10f20c5fddd76cccfce"}