Log In Sign Up

Bootstrapped Q-learning with Context Relevant Observation Pruning to Generalize in Text-based Games

by   Subhajit Chaudhury, et al.

We show that Reinforcement Learning (RL) methods for solving Text-Based Games (TBGs) often fail to generalize on unseen games, especially in small data regimes. To address this issue, we propose Context Relevant Episodic State Truncation (CREST) for irrelevant token removal in observation text for improved generalization. Our method first trains a base model using Q-learning, which typically overfits the training games. The base model's action token distribution is used to perform observation pruning that removes irrelevant tokens. A second bootstrapped model is then retrained on the pruned observation text. Our bootstrapped agent shows improved generalization in solving unseen TextWorld games, using 10x-20x fewer training games compared to previous state-of-the-art methods despite requiring less number of training episodes.


Counting to Explore and Generalize in Text-based Games

We propose a recurrent RL agent with an episodic exploration mechanism t...

Case-based Reasoning for Better Generalization in Text-Adventure Games

Text-based games (TBG) have emerged as promising environments for drivin...

Towards Solving Text-based Games by Producing Adaptive Action Spaces

To solve a text-based game, an agent needs to formulate valid text comma...

Learning Dynamic Knowledge Graphs to Generalize on Text-Based Games

Playing text-based games requires skill in processing natural language a...

Revisiting the Roles of "Text" in Text Games

Text games present opportunities for natural language understanding (NLU...

Attentive Mask CLIP

Image token removal is an efficient augmentation strategy for reducing t...