Fast Stochastic Policy Gradient: Negative Momentum for Reinforcement Learning

TL;DR

This paper introduces SPG-NM, a stochastic policy gradient algorithm with negative momentum, which accelerates convergence in reinforcement learning tasks while maintaining computational efficiency and robustness to hyper-parameters.

Contribution

The paper proposes a novel negative momentum technique for stochastic policy gradient methods, improving convergence speed without increasing computational complexity.

Findings

Faster convergence in bandit and MDP tasks compared to state-of-the-art algorithms.

Robustness of SPG-NM to hyper-parameter variations.

Maintains similar computational complexity as existing SPG algorithms.

Abstract

Stochastic optimization algorithms, particularly stochastic policy gradient (SPG), report significant success in reinforcement learning (RL). Nevertheless, up to now, that how to speedily acquire an optimal solution for RL is still a challenge. To tackle this issue, this work develops a fast SPG algorithm from the perspective of utilizing a momentum, coined SPG-NM. Specifically, in SPG-NM, a novel type of the negative momentum (NM) technique is applied into the classical SPG algorithm. Different from the existing NM techniques, we have adopted a few hyper-parameters in our SPG-NM algorithm. Moreover, the computational complexity is nearly same as the modern SPG-type algorithms, e.g., accelerated policy gradient (APG), which equips SPG with Nesterov's accelerated gradient (NAG). We evaluate the resulting algorithm on two classical tasks, bandit setting and Markov decision process (MDP). Numerical results in different tasks demonstrate faster convergence rate of the resulting algorithm by comparing state-of-the-art algorithms, which confirm the positive impact of NM in accelerating SPG for RL. Also, numerical experiments under different settings confirm the robustness of our SPG-NM algorithm for some certain crucial hyper-parameters, which ride the user feel free in practice.