Optimistic Task Inference for Behavior Foundation Models
This work addresses data and labeling challenges in zero-shot RL for AI systems, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the data inefficiency of Behavior Foundation Models (BFMs) in zero-shot reinforcement learning by proposing OpTI-BFM, an optimistic decision criterion for task inference through environment interaction, which enables BFMs to identify and optimize unseen reward functions in a handful of episodes with minimal compute overhead.
Behavior Foundation Models (BFMs) are capable of retrieving high-performing policy for any reward function specified directly at test-time, commonly referred to as zero-shot reinforcement learning (RL). While this is a very efficient process in terms of compute, it can be less so in terms of data: as a standard assumption, BFMs require computing rewards over a non-negligible inference dataset, assuming either access to a functional form of rewards, or significant labeling efforts. To alleviate these limitations, we tackle the problem of task inference purely through interaction with the environment at test-time. We propose OpTI-BFM, an optimistic decision criterion that directly models uncertainty over reward functions and guides BFMs in data collection for task inference. Formally, we provide a regret bound for well-trained BFMs through a direct connection to upper-confidence algorithms for linear bandits. Empirically, we evaluate OpTI-BFM on established zero-shot benchmarks, and observe that it enables successor-features-based BFMs to identify and optimize an unseen reward function in a handful of episodes with minimal compute overhead. Code is available at https://github.com/ThomasRupf/opti-bfm.