Generalised Policy Improvement with Geometric Policy Composition. (arXiv:2206.08736v1 [stat.ML])

Web: http://arxiv.org/abs/2206.08736

We introduce a method for policy improvement that interpolates between the
greedy approach of value-based reinforcement learning (RL) and the full
planning approach typical of model-based RL. The new method builds on the
concept of a geometric horizon model (GHM, also known as a gamma-model), which
models the discounted state-visitation distribution of a given policy. We show
that we can evaluate any non-Markov policy that switches between a set of base
Markov policies with fixed probability by a careful composition …

arxiv improvement ml policy