arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1708.04782cs.LGcs.AI
收藏

StarCraft II:强化学习的新挑战

StarCraft II: A New Challenge for Reinforcement Learning

DeepMind;Blizzard(暴雪娱乐)
Oriol Vinyals, Timo Ewalds, Sergey Bartunov, Petko Georgiev, Alexander Sasha Vezhnevets, Michelle Yeo, Alireza Makhzani, Heinrich Küttler, John Agapiou, Julian … 展开作者

Oriol Vinyals, Timo Ewalds, Sergey Bartunov, Petko Georgiev, Alexander Sasha Vezhnevets, Michelle Yeo, Alireza Makhzani, Heinrich Küttler, John Agapiou, Julian Schrittwieser, John Quan, Stephen Gaffney, Stig Petersen, Karen Simonyan, Tom Schaul, Hado van Hasselt, David Silver, Timothy Lillicrap, Kevin Calderone, Paul Keet, Anthony Brunasso, David Lawrence, Anders Ekermo, Jacob Repp, Rodney Tsing

摘要:

介绍了一个基于《星际争霸II》游戏的强化学习环境SC2 LE(StarCraft II Learning Environment)。这一领域对强化学习提出了新的巨大挑战,代表了比大多数先前工作中考虑的更困难的一类问题。这是一个多主体问题,多个玩家相互作用;由于部分观察到的地图,信息不完善;它有一个大的动作空间,涉及数百个单元的选择和控制;它有一个大的状态空间,必须只从原始输入特征平面观察;它延迟了信用分配,需要数千步的长期策略。我们描述了星际争霸II领域的观察,动作和奖励规范,并提供了一个开源的基于Python的接口与游戏引擎进行通信。除了主要的游戏地图,我们还提供了一套迷你游戏,专注于星际争霸II游戏的不同元素。对于主要的游戏地图,我们还提供了来自人类专家玩家的游戏重播数据的附带数据集。我们给出了从这些数据训练的神经网络的初始基线结果,以预测游戏结果和玩家行为。最后,我们给出了应用于星际争霸II领域的规范深度强化学习代理的初始基线结果。在迷你游戏中,这些智能体学习如何达到与新手玩家相当的游戏水平。然而,当在主要游戏上训练时,这些代理无法取得重大进展。因此,SC2 LE为探索深度强化学习算法和架构提供了一个新的和具有挑战性的环境。

英文摘要:

This paper introduces SC2LE (StarCraft II Learning Environment), a reinforcement learning environment based on the StarCraft II game. This domain poses a new grand challenge for reinforcement learning, representing a more difficult class of problems than considered in most prior work. It is a multi-agent problem with multiple players interacting; there is imperfect information due to a partially observed map; it has a large action space involving the selection and control of hundreds of units; it has a large state space that must be observed solely from raw input feature planes; and it has delayed credit assignment requiring long-term strategies over thousands of steps. We describe the observation, action, and reward specification for the StarCraft II domain and provide an open source Python-based interface for communicating with the game engine. In addition to the main game maps, we provide a suite of mini-games focusing on different elements of StarCraft II gameplay. For the main game maps, we also provide an accompanying dataset of game replay data from human expert players. We give initial baseline results for neural networks trained from this data to predict game outcomes and player actions. Finally, we present initial baseline results for canonical deep reinforcement learning agents applied to the StarCraft II domain. On the mini-games, these agents learn to achieve a level of play that is comparable to a novice player. However, when trained on the main game, these agents are unable to make significant progress. Thus, SC2LE offers a new and challenging environment for exploring deep reinforcement learning algorithms and architectures.

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。

↑