Past Recording
ShareStar
[GATA] Learning Dynamic Belief Graphs to Generalize on Text-Based Games
Wednesday Nov 11 2020 17:00 GMT
Please to join the live chat.
[GATA] Learning Dynamic Belief Graphs to Generalize on Text-Based Games
Why This Is Interesting

Playing text-based games requires skills in processing natural language and sequential decision making. Achieving human-level performance on text-based games remains an open challenge, and prior research has largely relied on hand-crafted structured representations and heuristics.

In this work, we investigate how an agent can plan and generalize in text-based games using graph-structured representations learned end-to-end from raw text. We propose a novel graph-aided transformer agent (GATA) that infers and updates latent belief graphs during planning to enable effective action selection by capturing the underlying game dynamics. GATA is trained using a combination of reinforcement and self-supervised learning.

Our work demonstrates that the learned graph-based representations help agents converge to better policies than their text-only counterparts and facilitate effective generalization across game configurations. Experiments on 500+ unique games from the TextWorld suite show that our best agent outperforms text-based baselines by an average of 24.2%.

Time of Recording: Wednesday Nov 11 2020 17:00 GMT