Continuous MDP Homomorphisms and Homomorphic Policy Gradient. (arXiv:2209.07364v1 [cs.LG])

Abstraction has been widely studied as a way to improve the efficiency and
generalization of reinforcement learning algorithms. In this paper, we study
abstraction in the continuous-control setting. We extend the definition of MDP
homomorphisms to encompass continuous actions in continuous state spaces. We
derive a policy gradient theorem on the abstract MDP, which allows us to
leverage approximate symmetries of the environment for policy optimization.
Based on this theorem, we propose an actor-critic algorithm that is able to
learn …

arxiv continuous gradient policy