Recurrent Control Nets for Deep Reinforcement Learning

TL;DR

This paper introduces Recurrent Control Nets (RCNs), combining RNNs and Structured Control Nets to produce rhythmic motion efficiently in reinforcement learning, outperforming traditional MLP baselines.

Contribution

The paper proposes RCNs, a novel architecture that integrates RNNs with structured control modules, enhancing rhythmic motion learning in reinforcement learning environments.

Findings

RCNs match or outperform MLPs and SCNs in various tasks.

RNNs effectively model biological CPGs in reinforcement learning.

SCN-like structures show promise in RL applications.

Abstract

Central Pattern Generators (CPGs) are biological neural circuits capable of producing coordinated rhythmic outputs in the absence of rhythmic input. As a result, they are responsible for most rhythmic motion in living organisms. This rhythmic control is broadly applicable to fields such as locomotive robotics and medical devices. In this paper, we explore the possibility of creating a self-sustaining CPG network for reinforcement learning that learns rhythmic motion more efficiently and across more general environments than the current multilayer perceptron (MLP) baseline models. Recent work introduces the Structured Control Net (SCN), which maintains linear and nonlinear modules for local and global control, respectively. Here, we show that time-sequence architectures such as Recurrent Neural Networks (RNNs) model CPGs effectively. Combining previous work with RNNs and SCNs, we introduce the Recurrent Control Net (RCN), which adds a linear component to the, RCNs match and exceed the performance of baseline MLPs and SCNs across all environment tasks. Our findings confirm existing intuitions for RNNs on reinforcement learning tasks, and demonstrate promise of SCN-like structures in reinforcement learning.