Data-efficient visuomotor policy training using reinforcement learning and generative models

TL;DR

This paper introduces a data-efficient framework combining reinforcement learning and generative models for visuomotor tasks, improving policy training efficiency and safety in robotic applications.

Contribution

It proposes a novel three-part training approach integrating latent variables, generative models, and supervised learning for visuomotor policies.

Findings

Enables safe exploration and reduces data requirements.

Provides measures to predict RL policy performance before physical training.

Analyzes generative model characteristics affecting policy success.

Abstract

We present a data-efficient framework for solving visuomotor sequential decision-making problems which exploits the combination of reinforcement learning (RL) and latent variable generative models. Our framework trains deep visuomotor policies by introducing an action latent variable such that the feed-forward policy search can be divided into three parts: (i) training a sub-policy that outputs a distribution over the action latent variable given a state of the system, (ii) unsupervised training of a generative model that outputs a sequence of motor actions conditioned on the latent action variable, and (iii) supervised training of the deep visuomotor policy in an end-to-end fashion. Our approach enables safe exploration and alleviates the data-inefficiency problem as it exploits prior knowledge about valid sequences of motor actions. Moreover, we provide a set of measures for evaluation of generative models such that we are able to predict the performance of the RL policy training prior to the actual training on a physical robot. We define two novel measures of disentanglement and local linearity for assessing the quality of latent representations, and complement them with existing measures for assessment of the learned distribution. We experimentally determine the characteristics of different generative models that have the most influence on performance of the final policy training on a robotic picking task.