Chaos-based reinforcement learning with TD3

TL;DR

This paper integrates the TD3 reinforcement learning algorithm into chaos-based RL, demonstrating its effectiveness in goal-reaching tasks and adaptive exploration-exploitation behavior driven by chaotic dynamics.

Contribution

It introduces the use of TD3 in chaos-based reinforcement learning, enabling better exploration and adaptation in continuous action spaces.

Findings

TD3 effectively learns in goal-reaching tasks within CBRL.

CBRL agents with TD3 can adapt exploration based on environmental changes.

Optimal chaos strength allows flexible switching between exploration and exploitation.

Abstract

Chaos-based reinforcement learning (CBRL) is a method in which the agent's internal chaotic dynamics drives exploration. However, the learning algorithms in CBRL have not been thoroughly developed in previous studies, nor have they incorporated recent advances in reinforcement learning. This study introduced Twin Delayed Deep Deterministic Policy Gradients (TD3), which is one of the state-of-the-art deep reinforcement learning algorithms that can treat deterministic and continuous action spaces, to CBRL. The validation results provide several insights. First, TD3 works as a learning algorithm for CBRL in a simple goal-reaching task. Second, CBRL agents with TD3 can autonomously suppress their exploratory behavior as learning progresses and resume exploration when the environment changes. Finally, examining the effect of the agent's chaoticity on learning shows that there exists a suitable range of chaos strength in the agent's model to flexibly switch between exploration and exploitation and adapt to environmental changes.