Goal Inference from Open-Ended Dialog
This work addresses the challenge of goal inference for embodied agents in domains like grocery shopping and home assistance, offering an incremental improvement over existing methods by combining online efficiency with flexibility.
The paper tackles the problem of enabling embodied agents to learn and accomplish diverse user goals from open-ended dialog, achieving results that outperform ablation baselines lacking explicit goal representation or probabilistic inference.
We present an online method for embodied agents to learn and accomplish diverse user goals. While offline methods like RLHF can represent various goals but require large datasets, our approach achieves similar flexibility with online efficiency. We extract natural language goal representations from conversations with Large Language Models (LLMs). We prompt an LLM to role play as a human with different goals and use the corresponding likelihoods to run Bayesian inference over potential goals. As a result, our method can represent uncertainty over complex goals based on unrestricted dialog. We evaluate our method in grocery shopping and home robot assistance domains using a text-based interface and AI2Thor simulation respectively. Results show our method outperforms ablation baselines that lack either explicit goal representation or probabilistic inference.