{"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/marathon-environments-multi-agent-continuous","title":"Marathon Environments: Multi-Agent Continuous Control Benchmarks in a Modern Video Game Engine","arxiv_id":"1902.09097","date":"2019-02-25","proceeding":null,"authors":["Joe Booth","Jackson Booth"],"abstract":"Recent advances in deep reinforcement learning in the paradigm of locomotion\nusing continuous control have raised the interest of game makers for the\npotential of digital actors using active ragdoll. Currently, the available\noptions to develop these ideas are either researchers' limited codebase or\nproprietary closed systems. We present Marathon Environments, a suite of open\nsource, continuous control benchmarks implemented on the Unity game engine,\nusing the Unity ML- Agents Toolkit. We demonstrate through these benchmarks\nthat continuous control research is transferable to a commercial game engine.\nFurthermore, we exhibit the robustness of these environments by reproducing\nadvanced continuous control research, such as learning to walk, run and\nbackflip from motion capture data; learning to navigate complex terrains; and\nby implementing a video game input control system. We show further robustness\nby training with alternative algorithms found in OpenAI.Baselines. Finally, we\nshare strategies for significantly reducing the training time.","url_abs":"http://arxiv.org/abs/1902.09097v1","url_pdf":"http://arxiv.org/pdf/1902.09097v1.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":"marathon-environments-multi-agent-continuous","repo_url":"https://github.com/Unity-Technologies/marathon-envs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"navigate","task_name":"Navigate"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"unity","task_name":"Unity"},{"task_slug":"continuous-control","task_name":"continuous-control"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}