Counting to Explore and Generalize in Text-based Games
Published in
arXiv.org(2018)External Links:
TL
TL;DR
A recurrent RL agent with an episodic exploration mechanism that helps discovering good policies in text-based game environments and observes that the agent learns policies that generalize to unseen games of greater difficulty.
Abstract
We propose a recurrent RL agent with an episodic exploration mechanism that helps discovering good policies in text-based game environments. We show promising results on a set of generated text-based games of varying difficulty where the goal is to collect a coin located at the end of a chain of rooms. In contrast to previous text-based RL approaches, we observe that our agent learns policies that generalize to unseen games of greater difficulty.
References24 items
1
TextWorld: A Learning Environment for Text-based Games
2
Automatic differentiation in PyTorch
3
Count-Based Exploration in Feature Space for Reinforcement Learning
4
Parameter Space Noise for Exploration
5