Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters. (arXiv:2205.13703v1 [cs.LG])

Motivated by the success of ensembles for uncertainty estimation in
supervised learning, we take a renewed look at how ensembles of $Q$-functions
can be leveraged as the primary source of pessimism for offline reinforcement
learning (RL). We begin by identifying a critical flaw in a popular algorithmic
choice used by many ensemble-based RL algorithms, namely the use of shared
pessimistic target values when computing each ensemble member's Bellman error.
Through theoretical analyses and construction of examples in toy MDPs, we …

arxiv rl