# Towards Solving Text-based Games by Producing Adaptive Action Spaces

arXiv: https://arxiv.org/abs/1812.00855 · HTML: https://mlsanity.com/paper/1812.00855/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2018.

## Built on by (most cited first, 5 of 5)

- [A Survey of Text Games for Reinforcement Learning informed by Natural Language](https://mlsanity.com/paper/2109.09478/) (2021)
- [Perceiving the World: Question-guided Reinforcement Learning for Text-based Games](https://mlsanity.com/paper/2204.09597/) (2022)
- [Action Assembly: Sparse Imitation Learning for Text Based Games with Combinatorial Action Spaces](https://mlsanity.com/paper/1905.09700/) (2019)
- [Positive Experience Reflection for Agents in Interactive Text Environments](https://mlsanity.com/paper/2411.02223/) (2024)
- [Affordance Extraction with an External Knowledge Database for Text-Based Simulated Environments](https://mlsanity.com/paper/2207.00265/) (2022)

## Abstract (arXiv)

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 F1 score on the test set.