ELF：一个可扩展的、轻量级的、灵活的实时的策略游戏研究平台
ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games
摘要：
在本文中，我们提出了ELF，一个广泛的，轻量级的和灵活的基础强化学习研究平台。使用ELF，我们实现了一个高度可定制的实时的【形】策略（RTS）引擎，具有三个游戏环境（迷你RTS，夺旗和塔防）。Mini-RTS作为《星际争霸》的微缩版，能够捕捉关键的游戏动态，并在Macbook Pro笔记本电脑上以每核心40 K帧每秒（FPS）的速度运行。当与现代强化学习方法相结合时，该系统可以在一天内使用6个CPU和1个GPU对内置AI进行端到端的训练完整的游戏机器人。此外，我们的平台是灵活的环境智能体通信拓扑结构，RL方法的选择，游戏参数的变化，并可以托管现有的C/C++为基础的游戏环境，如街机学习环境。使用ELF，我们彻底探索了训练参数，并表明具有Leaky ReLU和批量归一化以及长期训练和渐进课程的网络在Mini-RTS的完整游戏中击败了基于规则的内置AI超过$70\%$。在其他两场比赛中也取得了不错的成绩。在游戏回放中，我们展示了我们的代理学习有趣的策略。ELF及其RL平台在https://github.com/facebookresearch/ELF上开源。
英文摘要：
In this paper, we propose ELF, an Extensive, Lightweight and Flexible platform for fundamental reinforcement learning research. Using ELF, we implement a highly customizable real-time strategy (RTS) engine with three game environments (Mini-RTS, Capture the Flag and Tower Defense). Mini-RTS, as a miniature version of StarCraft, captures key game dynamics and runs at 40K frame-per-second (FPS) per core on a Macbook Pro notebook. When coupled with modern reinforcement learning methods, the system can train a full-game bot against built-in AIs end-to-end in one day with 6 CPUs and 1 GPU. In addition, our platform is flexible in terms of environment-agent communication topologies, choices of RL methods, changes in game parameters, and can host existing C/C++-based game environments like Arcade Learning Environment. Using ELF, we thoroughly explore training parameters and show that a network with Leaky ReLU and Batch Normalization coupled with long-horizon training and progressive curriculum beats the rule-based built-in AI more than $70\%$ of the time in the full game of Mini-RTS. Strong performance is also achieved on the other two games. In game replays, we show our agents learn interesting strategies. ELF, along with its RL platform, is open-sourced at https://github.com/facebookresearch/ELF.
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。
