Potential-based reward shaping for learning to play text-based adventure games

Anonymous

Abstract: Text-based games are an optimal testbed for language-based reinforcement learning (RL). In previous work, deep Q-learning is commonly used as the learning agent. Q-learning algorithms are challenging to apply to complex real-world domains due to, for example, their instability in training. Therefore, in this paper, we adapt the soft-actor-critic (SAC) algorithm to the text-based environment. To deal with sparse extrinsic rewards from the environment, we propose a potential-based reward shaping technique to provide more informative (dense) reward signals to the RL agent. We apply our method to play difficult text-based games. Our SAC method achieves higher scores than the Q-learning methods on many games with only half the number of training steps. This shows that it is well-suited for text-based games. Moreover, we show that the reward-shaping technique helps the agent to learn the policy faster and achieve higher scores.

Paper Type: long

Research Area: Dialogue and Interactive Systems