Double Actor-Critic with TD Error-Driven Regularization in Reinforcement Learning

TL;DR

This paper introduces TDDR, a novel double actor-critic reinforcement learning algorithm with TD error-driven regularization, achieving superior value estimation without extra hyperparameters and demonstrating strong performance in continuous control tasks.

Contribution

TDDR is the first to combine double actor-critic architecture with TD error-driven regularization without adding hyperparameters, improving value estimation in reinforcement learning.

Findings

TDDR outperforms benchmark algorithms in continuous control tasks.

TDDR achieves better value estimation compared to classical methods.

The algorithm simplifies implementation by avoiding additional hyperparameters.

Abstract

To obtain better value estimation in reinforcement learning, we propose a novel algorithm based on the double actor-critic framework with temporal difference error-driven regularization, abbreviated as TDDR. TDDR employs double actors, with each actor paired with a critic, thereby fully leveraging the advantages of double critics. Additionally, TDDR introduces an innovative critic regularization architecture. Compared to classical deterministic policy gradient-based algorithms that lack a double actor-critic structure, TDDR provides superior estimation. Moreover, unlike existing algorithms with double actor-critic frameworks, TDDR does not introduce any additional hyperparameters, significantly simplifying the design and implementation process. Experiments demonstrate that TDDR exhibits strong competitiveness compared to benchmark algorithms in challenging continuous control tasks.