Building generalist agents that can accomplish many goals in rich open-ended environments is one of the research frontiers for reinforcement learning. A key limiting factor for building generalist agents with RL has been the need for a large number of reward functions for achieving different goals. We investigate the feasibility of using off-the-shelf vision-language models, or VLMs, as sources of rewards for reinforcement learning agents. We show how rewards for visual achievement of a variety of language goals can be derived from the CLIP family of models, and used to train RL agents that can achieve a variety of language goals. We showcase this approach in two distinct visual domains and present a scaling trend showing how larger VLMs lead to more accurate rewards for visual goal achievement, which in turn produces more capable RL agents.

We present a model-agnostic algorithm for generating post-hoc explanations and uncertainty intervals for a machine learning model when only a static sample of inputs and outputs from the model is available, rather than direct access to the model itself. This situation may arise when model evaluations are expensive; when privacy, security and bandwidth constraints are imposed; or when there is a need for real-time, on-device explanations. Our algorithm uses a bootstrapping approach to quantify the uncertainty that inevitably arises when generating explanations from a finite sample of model queries. Through a simulation study, we show that the uncertainty intervals generated by our algorithm exhibit a favorable trade-off between interval width and coverage probability compared to the naive confidence intervals from classical regression analysis as well as current Bayesian approaches for quantifying explanation uncertainty. We further demonstrate the capabilities of our method by applying it to black-box models, including a deep neural network, trained on three real-world datasets.