Exploiting Domain Symmetries in Reinforcement Learning with Continuous State and Action Spaces

A central problem in reinforcement learning is how to deal with large state and action spaces. When the problem domain presents intrinsic symmetries, exploiting them can be key to achieve good performance. We analyze the gains that can be effectively achieved by exploiting different kinds of symmetries, and the effect of combining them, in a test case: the stand-up and stabilization of an inverted pendulum.