Think Before You Act: Unified Policy for Interleaving Language Reasoning with Actions
This work addresses the challenge of leveraging language data for more interpretable and effective AI agents in reinforcement learning, representing an incremental advancement in combining language models with action policies.
The paper tackles the problem of integrating language reasoning with action generation in reinforcement learning by proposing a unified policy that interleaves textual captions with actions, and it shows consistent performance improvements over a caption-free baseline on the most challenging BabyAI task.
The success of transformer models trained with a language modeling objective brings a promising opportunity to the reinforcement learning framework. Decision Transformer is a step towards this direction, showing how to train transformers with a similar next-step prediction objective on offline data. Another important development in this area is the recent emergence of large-scale datasets collected from the internet, such as the ones composed of tutorial videos with captions where people talk about what they are doing. To take advantage of this language component, we propose a novel method for unifying language reasoning with actions in a single policy. Specifically, we augment a transformer policy with word outputs, so it can generate textual captions interleaved with actions. When tested on the most challenging task in BabyAI, with captions describing next subgoals, our reasoning policy consistently outperforms the caption-free baseline.