On-Robot Policy Learning with $\mathrm{O}(2)$-Equivariant SAC

Recently, equivariant neural network models have been shown to be useful in improving sample efficiency for tasks in computer vision and reinforcement learning. This paper explores this idea in the context of on-robot policy learning where a policy must be learned entirely on a physical robotic system without reference to a model, a simulator, or an offline dataset. We focus on applications of $\mathrm{SO}(2)$-Equivariant SAC to robotic manipulation and explore a number of variations of the algorithm. Ultimately, we demonstrate the ability to learn several non-trivial manipulation tasks completely through on-robot experiences in less than an hour or two of wall clock time.