Value Activation for Bias Alleviation: Generalized-activated Deep Double Deterministic Policy Gradients

TL;DR

This paper introduces GD3, a novel reinforcement learning algorithm that employs a generalized-activated weighting operator to improve value estimation, effectively reducing bias and enhancing performance in continuous control tasks.

Contribution

It proposes a new bias correction method using activation functions in value estimation, leading to a versatile and effective algorithm for deep reinforcement learning.

Findings

GD3 alleviates estimation bias in value functions.

Activation functions improve convergence speed and performance.

Task-specific activation functions outperform standard baselines.

Abstract

It is vital to accurately estimate the value function in Deep Reinforcement Learning (DRL) such that the agent could execute proper actions instead of suboptimal ones. However, existing actor-critic methods suffer more or less from underestimation bias or overestimation bias, which negatively affect their performance. In this paper, we reveal a simple but effective principle: proper value correction benefits bias alleviation, where we propose the generalized-activated weighting operator that uses any non-decreasing function, namely activation function, as weights for better value estimation. Particularly, we integrate the generalized-activated weighting operator into value estimation and introduce a novel algorithm, Generalized-activated Deep Double Deterministic Policy Gradients (GD3). We theoretically show that GD3 is capable of alleviating the potential estimation bias. We interestingly find that simple activation functions lead to satisfying performance with no additional tricks, and could contribute to faster convergence. Experimental results on numerous challenging continuous control tasks show that GD3 with task-specific activation outperforms the common baseline methods. We also uncover a fact that fine-tuning the polynomial activation function achieves superior results on most of the tasks.