{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FTQFO6ZLFVBZJQJAXPQ3PZPSCI","short_pith_number":"pith:FTQFO6ZL","schema_version":"1.0","canonical_sha256":"2ce0577b2b2d4394c120bbe1b7e5f21225b028222545a040c335220ced00b8db","source":{"kind":"arxiv","id":"2003.11102","version":1},"attestation_state":"computed","paper":{"title":"Learning to Play Soccer by Reinforcement and Applying Sim-to-Real to Compete in the Real World","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alain Tapp, Hansenclever F. Bassani, Heitor R. Medeiros, Jose Nilton de O. Lima Junior, Pedro H. M. Braga, Renie A. Delgado","submitted_at":"2020-03-24T20:23:18Z","abstract_excerpt":"This work presents an application of Reinforcement Learning (RL) for the complete control of real soccer robots of the IEEE Very Small Size Soccer (VSSS), a traditional league in the Latin American Robotics Competition (LARC). In the VSSS league, two teams of three small robots play against each other. We propose a simulated environment in which continuous or discrete control policies can be trained, and a Sim-to-Real method to allow using the obtained policies to control a robot in the real world. The results show that the learned policies display a broad repertoire of behaviors that are diff"},"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":"2003.11102","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-03-24T20:23:18Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"6f30890dd731fb9216afc777083a17b71776efa5d715851b3f4e5fa6e693a473","abstract_canon_sha256":"7ae072bc24b81a60511171cf9afb42de6760100bdb5ca96e1bb86a205d1990be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:50:30.953377Z","signature_b64":"zltCuA/f1AIxS0EFPkRPwzCC3SNrbLhb4lKHnrDRy11sGtzMSDI9gwoNVap7mU+8Dsx7T9OKcbi4FaxuHJBFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ce0577b2b2d4394c120bbe1b7e5f21225b028222545a040c335220ced00b8db","last_reissued_at":"2026-07-05T00:50:30.952976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:50:30.952976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Play Soccer by Reinforcement and Applying Sim-to-Real to Compete in the Real World","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alain Tapp, Hansenclever F. Bassani, Heitor R. Medeiros, Jose Nilton de O. Lima Junior, Pedro H. M. Braga, Renie A. Delgado","submitted_at":"2020-03-24T20:23:18Z","abstract_excerpt":"This work presents an application of Reinforcement Learning (RL) for the complete control of real soccer robots of the IEEE Very Small Size Soccer (VSSS), a traditional league in the Latin American Robotics Competition (LARC). In the VSSS league, two teams of three small robots play against each other. We propose a simulated environment in which continuous or discrete control policies can be trained, and a Sim-to-Real method to allow using the obtained policies to control a robot in the real world. The results show that the learned policies display a broad repertoire of behaviors that are diff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.11102","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/2003.11102/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":"2003.11102","created_at":"2026-07-05T00:50:30.953038+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.11102v1","created_at":"2026-07-05T00:50:30.953038+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.11102","created_at":"2026-07-05T00:50:30.953038+00:00"},{"alias_kind":"pith_short_12","alias_value":"FTQFO6ZLFVBZ","created_at":"2026-07-05T00:50:30.953038+00:00"},{"alias_kind":"pith_short_16","alias_value":"FTQFO6ZLFVBZJQJA","created_at":"2026-07-05T00:50:30.953038+00:00"},{"alias_kind":"pith_short_8","alias_value":"FTQFO6ZL","created_at":"2026-07-05T00:50:30.953038+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/FTQFO6ZLFVBZJQJAXPQ3PZPSCI","json":"https://pith.science/pith/FTQFO6ZLFVBZJQJAXPQ3PZPSCI.json","graph_json":"https://pith.science/api/pith-number/FTQFO6ZLFVBZJQJAXPQ3PZPSCI/graph.json","events_json":"https://pith.science/api/pith-number/FTQFO6ZLFVBZJQJAXPQ3PZPSCI/events.json","paper":"https://pith.science/paper/FTQFO6ZL"},"agent_actions":{"view_html":"https://pith.science/pith/FTQFO6ZLFVBZJQJAXPQ3PZPSCI","download_json":"https://pith.science/pith/FTQFO6ZLFVBZJQJAXPQ3PZPSCI.json","view_paper":"https://pith.science/paper/FTQFO6ZL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.11102&json=true","fetch_graph":"https://pith.science/api/pith-number/FTQFO6ZLFVBZJQJAXPQ3PZPSCI/graph.json","fetch_events":"https://pith.science/api/pith-number/FTQFO6ZLFVBZJQJAXPQ3PZPSCI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FTQFO6ZLFVBZJQJAXPQ3PZPSCI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FTQFO6ZLFVBZJQJAXPQ3PZPSCI/action/storage_attestation","attest_author":"https://pith.science/pith/FTQFO6ZLFVBZJQJAXPQ3PZPSCI/action/author_attestation","sign_citation":"https://pith.science/pith/FTQFO6ZLFVBZJQJAXPQ3PZPSCI/action/citation_signature","submit_replication":"https://pith.science/pith/FTQFO6ZLFVBZJQJAXPQ3PZPSCI/action/replication_record"}},"created_at":"2026-07-05T00:50:30.953038+00:00","updated_at":"2026-07-05T00:50:30.953038+00:00"}