{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/off-policy-general-value-functions-to","title":"Off-Policy General Value Functions to Represent Dynamic Role Assignments in RoboCup 3D Soccer Simulation","arxiv_id":"1402.4525","date":"2014-02-18","proceeding":null,"authors":["Saminda Abeyruwan","Andreas Seekircher","Ubbo Visser"],"abstract":"Collecting and maintaining accurate world knowledge in a dynamic, complex,\nadversarial, and stochastic environment such as the RoboCup 3D Soccer\nSimulation is a challenging task. Knowledge should be learned in real-time with\ntime constraints. We use recently introduced Off-Policy Gradient Descent\nalgorithms within Reinforcement Learning that illustrate learnable knowledge\nrepresentations for dynamic role assignments. The results show that the agents\nhave learned competitive policies against the top teams from the RoboCup 2012\ncompetitions for three vs three, five vs five, and seven vs seven agents. We\nhave explicitly used subsets of agents to identify the dynamics and the\nsemantics for which the agents learn to maximize their performance measures,\nand to gather knowledge about different objectives, so that all agents\nparticipate effectively and efficiently within the group.","url_abs":"http://arxiv.org/abs/1402.4525v1","url_pdf":"http://arxiv.org/pdf/1402.4525v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"off-policy-general-value-functions-to","repo_url":"https://github.com/samindaa/RLLib","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"world-knowledge","task_name":"World Knowledge"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}