TextWorld: A Learning Environment for Text-based Games
TextWorld: A Learning Environment for Text-based Games
复制标题
TextWorld：基于文本的游戏的学习环境
DOI：
10.1007/978-3-030-24337-1_3
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Adam Trischler
中科院分区：
文献类型：
--
作者：
Marc;Ákos Kádár;Xingdi Yuan;Ben A. Kybartas;Tavian Barnes;Emery Fine;James Moore;Matthew J. Hausknecht;Layla El Asri;Mahmoud Adada;Wendy Tay;Adam Trischler
我们介绍了TextWorld，一个沙盒学习环境，用于培训和评估基于文本的游戏中的RL代理。TextWorld是一个Python库，它处理文本游戏的交互式播放，以及状态跟踪和奖励分配等后端功能。它附带了一份精心策划的游戏清单，我们已经分析了这些游戏的特点和挑战。更重要的是，它使用户能够手工或自动生成新游戏。其生成机制可以精确控制构建游戏的难度、范围和语言，并可用于缓解商业文本游戏固有的挑战，如部分可观察性和稀少奖励。通过生成一组不同但相似的游戏，TextWorld还可以用于研究泛化和迁移学习。我们将基于文本的游戏转换为强化学习的形式，使用我们的框架开发了一组基准游戏，并对该集合和策划列表上的几个基线代理进行了评估。
We introduce TextWorld, a sandbox learning environment for the training and evaluation of RL agents on text-based games. TextWorld is a Python library that handles interactive play-through of text games, as well as backend functions like state tracking and reward assignment. It comes with a curated list of games whose features and challenges we have analyzed. More significantly, it enables users to handcraft or automatically generate new games. Its generative mechanisms give precise control over the difficulty, scope, and language of constructed games, and can be used to relax challenges inherent to commercial text games like partial observability and sparse rewards. By generating sets of varied but similar games, TextWorld can also be used to study generalization and transfer learning. We cast text-based games in the Reinforcement Learning formalism, use our framework to develop a set of benchmark games, and evaluate several baseline agents on this set and the curated list.