Towards Solving Text-based Games by Producing Adaptive Action Spaces
By Ruo Yu Tao, Marc-Alexandre Côté, Xingdi Yuan, Layla El Asri. 2018
14 citations recorded by the source corpus.
To solve a text-based game, an agent needs to formulate valid text commands for a given context and find the ones that lead to success. Recent attempts at solving text-based games with deep reinforcement learning have focused on the latter, i.e., learning to act optimally when valid actions are known in advance. In this work, we propose to tackle the first task and train a model that generates the set of all valid commands for a given context. We try three generative models on a dataset generated with Textworld. The best model can generate valid commands which were unseen at training and achieve high $F_1$ score on the test set.
Subfields: Artificial Intelligence, Natural Language Processing, Reinforcement Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Sergey Levine
- Yoshua Bengio
- Doina Precup
- William Fedus
- Prithviraj Ammanabrolu
- Pieter Abbeel
- Marc G. Bellemare
- Mark O. Riedl
In Natural Language Processing
- Mark O. Riedl
- Prithviraj Ammanabrolu
- William Broniec
- Doina Precup
- Hugo Larochelle
- Marc G. Bellemare
- William Fedus
- Yejin Choi
In Reinforcement Learning
- Sergey Levine
- Marc G. Bellemare
- Doina Precup
- William Fedus
- Hugo Larochelle
- Pieter Abbeel
- Prithviraj Ammanabrolu
- Chelsea Finn
Citations in the corpus
- Toward Automated Quest Generation in Text-Adventure Games (2019, background): “…(Bordes et al., 2010; He et al., 2016; Narasimhan et al., 2015; Fulda et al., 2017; Yang et al., 2018; Haroush et al., 2018; Cˆot´e et al., 2018; Tao et al., 2018; Ammanabrolu and Riedl, 2019a; Hausknecht et al., 2019a; Am-manabrolu and Riedl, 2019b; Hausknecht et al., 2019b), these works focus…”
- Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learning (2018, background): “A growing body of research has explored the challenges associated with text-based games (Bordes et al., 2010; Narasimhan et al., 2015; He et al., 2016; Fulda et al., 2017; Haroush et al., 2018; Cˆot´e et al., 2018; Tao et al., 2018).”
- Algorithmic Improvements for Deep Reinforcement Learning applied to Interactive Fiction (2019, background): “Admissible action set learning: Tao et al. (2018) approach the issue of learning admissible set given context as a supervised learning one.”