Model-Based Uncertainty in Value Functions
This work addresses inefficient exploration in reinforcement learning by providing sharper uncertainty estimates, which is an incremental improvement over previous methods.
The paper tackles the problem of quantifying uncertainty over expected cumulative rewards in model-based reinforcement learning, proposing a new uncertainty Bellman equation that converges to the true posterior variance and improves sample-efficiency in exploration tasks.
We consider the problem of quantifying uncertainty over expected cumulative rewards in model-based reinforcement learning. In particular, we focus on characterizing the variance over values induced by a distribution over MDPs. Previous work upper bounds the posterior variance over values by solving a so-called uncertainty Bellman equation, but the over-approximation may result in inefficient exploration. We propose a new uncertainty Bellman equation whose solution converges to the true posterior variance over values and explicitly characterizes the gap in previous work. Moreover, our uncertainty quantification technique is easily integrated into common exploration strategies and scales naturally beyond the tabular setting by using standard deep reinforcement learning architectures. Experiments in difficult exploration tasks, both in tabular and continuous control settings, show that our sharper uncertainty estimates improve sample-efficiency.