Variational Recurrent Models for Solving Partially Observable Control Tasks

TL;DR

This paper introduces a variational recurrent model-based reinforcement learning algorithm designed to improve performance in partially observable control tasks by enhancing environment modeling and policy learning.

Contribution

The paper presents a novel RL algorithm combining a variational recurrent model with an RL controller, specifically addressing partial observability in robotic control tasks.

Findings

Achieved better data efficiency than alternative methods.

Learned more optimal policies in complex PO tasks.

Effective in environments with long-term memory requirements.

Abstract

In partially observable (PO) environments, deep reinforcement learning (RL) agents often suffer from unsatisfactory performance, since two problems need to be tackled together: how to extract information from the raw observations to solve the task, and how to improve the policy. In this study, we propose an RL algorithm for solving PO tasks. Our method comprises two parts: a variational recurrent model (VRM) for modeling the environment, and an RL controller that has access to both the environment and the VRM. The proposed algorithm was tested in two types of PO robotic control tasks, those in which either coordinates or velocities were not observable and those that require long-term memorization. Our experiments show that the proposed algorithm achieved better data efficiency and/or learned more optimal policy than other alternative approaches in tasks in which unobserved states cannot be inferred from raw observations in a simple manner.