Unveiling Options with Neural Decomposition

TL;DR

This paper presents a neural decomposition method for reinforcement learning policies, enabling the extraction of reusable options from neural networks to improve generalization and accelerate learning across related tasks.

Contribution

It introduces a novel algorithm that decomposes neural network policies into sub-policies as options, facilitating transfer and reuse in reinforcement learning.

Findings

Successfully identifies useful options in grid-world domains

Accelerates learning on related tasks

Demonstrates effectiveness in complex exploration scenarios

Abstract

In reinforcement learning, agents often learn policies for specific tasks without the ability to generalize this knowledge to related tasks. This paper introduces an algorithm that attempts to address this limitation by decomposing neural networks encoding policies for Markov Decision Processes into reusable sub-policies, which are used to synthesize temporally extended actions, or options. We consider neural networks with piecewise linear activation functions, so that they can be mapped to an equivalent tree that is similar to oblique decision trees. Since each node in such a tree serves as a function of the input of the tree, each sub-tree is a sub-policy of the main policy. We turn each of these sub-policies into options by wrapping it with while-loops of varied number of iterations. Given the large number of options, we propose a selection mechanism based on minimizing the Levin loss for a uniform policy on these options. Empirical results in two grid-world domains where exploration can be difficult confirm that our method can identify useful options, thereby accelerating the learning process on similar but different tasks.