VariBAD: A Very Good Method for Bayes−Adaptive Deep RL via Meta−Learning
Luisa Zintgraf‚ Kyriacos Shiarlis‚ Maximilian Igl‚ Sebastian Schulze‚ Yarin Gal‚ Katja Hofmann and Shimon Whiteson
Trading off exploration and exploitation in an unknown environment is key to maximising expected return during learning. A Bayes-optimal policy, which does so optimally, conditions its actions not only on the environment state but on the agent's uncertainty about the environment. Computing a Bayes-optimal policy is however intractable for all but the smallest tasks. In this paper, we introduce variational Bayes-Adaptive Deep RL (variBAD), a way to meta-learn to perform approximate inference in an unknown environment, and incorporate task uncertainty directly during action selection. In a grid-world domain, we illustrate how \acro performs structured online exploration as a function of task uncertainty. We further evaluate \acro on MuJoCo domains widely used in meta-RL and show that it achieves higher online return than existing methods.