Marathon Environments：现代视频游戏引擎中的多智能体连续控制基准
Marathon Environments: Multi-Agent Continuous Control Benchmarks in a Modern Video Game Engine
摘要：
深度强化学习在使用连续控制的运动范例中的最新进展已经引起了游戏制作者对使用主动布娃娃的数字演员的潜力的兴趣。目前，开发这些想法的可用选项要么是研究人员有限的代码库，要么是专有的封闭系统。我们提出了马拉松环境，一套开源的，连续的控制基准在Unity游戏引擎上实现，使用Unity ML-代理工具包。通过这些基准测试，我们证明了持续控制研究可以转移到商业游戏引擎中。此外，我们展示了这些环境的鲁棒性再现先进的连续控制研究，如学习走路，跑步和后空翻从运动捕捉数据;学习导航复杂的地形;并通过实现视频游戏输入控制系统。我们通过使用OpenAI.Baselines中找到的替代算法进行训练，展示了进一步的鲁棒性。最后，我们分享显著减少训练时间的策略。
英文摘要：
Recent advances in deep reinforcement learning in the paradigm of locomotion using continuous control have raised the interest of game makers for the potential of digital actors using active ragdoll. Currently, the available options to develop these ideas are either researchers' limited codebase or proprietary closed systems. We present Marathon Environments, a suite of open source, continuous control benchmarks implemented on the Unity game engine, using the Unity ML- Agents Toolkit. We demonstrate through these benchmarks that continuous control research is transferable to a commercial game engine. Furthermore, we exhibit the robustness of these environments by reproducing advanced continuous control research, such as learning to walk, run and backflip from motion capture data; learning to navigate complex terrains; and by implementing a video game input control system. We show further robustness by training with alternative algorithms found in OpenAI.Baselines. Finally, we share strategies for significantly reducing the training time.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
