arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.01378cs.AIcs.LG
收藏

障碍塔:视觉、控制和规划中的泛化挑战

Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning

Unity Technologies(Unity科技公司);New York University(纽约大学)

Arthur Juliani, Ahmed Khalifa, Vincent-Pierre Berges, Jonathan Harper, Ervin Teng, Hunter Henry, Adam Crespi, Julian Togelius, Danny Lange

摘要:

最近人工智能研究的快速发展在一定程度上是由快速和具有挑战性的模拟环境的存在所推动的。这些环境通常采取游戏的形式;任务范围从简单的棋盘游戏到竞争性视频游戏。我们提出了一个新的基准-障碍塔:高保真,三维,第三人称,程序生成的环境。一个玩障碍塔的智能体必须学会同时解决低级控制和高级规划问题,同时从像素和稀疏的奖励信号中学习。与其他基准测试(如Arcade Learning Environment)不同,Obstacle Tower中对代理性能的评估是基于代理在环境中看不见的实例上表现良好的能力。在本文中,我们概述了环境,并提供了一组由当前最先进的深度RL方法以及人类玩家产生的基线结果。这些算法无法产生能够接近人类水平的代理。

英文摘要:

The rapid pace of recent research in AI has been driven in part by the presence of fast and challenging simulation environments. These environments often take the form of games; with tasks ranging from simple board games, to competitive video games. We propose a new benchmark - Obstacle Tower: a high fidelity, 3D, 3rd person, procedurally generated environment. An agent playing Obstacle Tower must learn to solve both low-level control and high-level planning problems in tandem while learning from pixels and a sparse reward signal. Unlike other benchmarks such as the Arcade Learning Environment, evaluation of agent performance in Obstacle Tower is based on an agent's ability to perform well on unseen instances of the environment. In this paper we outline the environment and provide a set of baseline results produced by current state-of-the-art Deep RL methods as well as human players. These algorithms fail to produce agents capable of performing near human level.

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。

↑