arXiv (Cornell University) · 2018 · 96 citations · 21 references
ComputingComputer ScienceArtificial IntelligenceMachine LearningNatural Language ProcessingGame PlayingGame-based LearningPolicy LearningReinforcement LearningReinforcement Learning FoundationsGame-playing AgentsLearning Environment DesignLearning From Sparse RewardsPartial ObservabilityReinforcement Learning For Game PlayingReinforcement Learning In GamesReinforcement Learning TransferTransfer Reinforcement Learning
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.
21
Human-level control through deep reinforcement learning
Volodymyr Mnih, Koray Kavukcuoglu, David Silver et al. · Nature · 2015 · 30K citations
Reinforcement Learning: An Introduction
IEEE Transactions on Neural Networks · 2005 · 25.8K citations
Artificial intelligence: a modern approach
Choice Reviews Online · 1995 · 22.2K citations · Full text
Yoshua Bengio, Jérôme Louradour, Ronan Collobert et al. · 2009 · 5K citations · Full text