Variational Policy Search using Sparse Gaussian Process Priors for Learning Multimodal Optimal Actions

TL;DR

This paper introduces two novel non-parametric policy search algorithms using sparse Gaussian processes to effectively learn multiple optimal actions in complex robotic tasks, overcoming limitations of unimodal policies.

Contribution

It presents multimodal and mode-seeking sparse Gaussian process policy search methods that handle multiple optimal actions, advancing non-parametric reinforcement learning techniques.

Findings

Effective in capturing multiple optimal actions in simulations

Improved policy flexibility for complex tasks

Demonstrated on object manipulation tasks

Abstract

Policy search reinforcement learning has been drawing much attention as a method of learning a robot control policy. In particular, policy search using such non-parametric policies as Gaussian process regression can learn optimal actions with high-dimensional and redundant sensors as input. However, previous methods implicitly assume that the optimal action becomes unique for each state. This assumption can severely limit such practical applications as robot manipulations since designing a reward function that appears in only one optimal action for complex tasks is difficult. The previous methods might have caused critical performance deterioration because the typical non-parametric policies cannot capture the optimal actions due to their unimodality. We propose novel approaches in non-parametric policy searches with multiple optimal actions and offer two different algorithms commonly based on a sparse Gaussian process prior and variational Bayesian inference. The following are the key ideas: 1) multimodality for capturing multiple optimal actions and 2) mode-seeking for capturing one optimal action by ignoring the others. First, we propose a multimodal sparse Gaussian process policy search that uses multiple overlapped GPs as a prior. Second, we propose a mode-seeking sparse Gaussian process policy search that uses the student-t distribution for a likelihood function. The effectiveness of those algorithms is demonstrated through applications to object manipulation tasks with multiple optimal actions in simulations.