Pretraining Deep Actor-Critic Reinforcement Learning Algorithms With Expert Demonstrations

TL;DR

This paper introduces a novel method for pretraining actor-critic reinforcement learning algorithms using expert demonstrations, improving training efficiency without relying on the global optimality assumption.

Contribution

It presents a theoretically grounded approach to pretrain both policy and value functions in actor-critic algorithms using expert demonstrations, addressing instability issues.

Findings

Outperforms non-pretrained algorithms in experiments

Enhances simulation efficiency of RL training

Applicable to DDPG and ACER algorithms

Abstract

Pretraining with expert demonstrations have been found useful in speeding up the training process of deep reinforcement learning algorithms since less online simulation data is required. Some people use supervised learning to speed up the process of feature learning, others pretrain the policies by imitating expert demonstrations. However, these methods are unstable and not suitable for actor-critic reinforcement learning algorithms. Also, some existing methods rely on the global optimum assumption, which is not true in most scenarios. In this paper, we employ expert demonstrations in a actor-critic reinforcement learning framework, and meanwhile ensure that the performance is not affected by the fact that expert demonstrations are not global optimal. We theoretically derive a method for computing policy gradients and value estimators with only expert demonstrations. Our method is theoretically plausible for actor-critic reinforcement learning algorithms that pretrains both policy and value functions. We apply our method to two of the typical actor-critic reinforcement learning algorithms, DDPG and ACER, and demonstrate with experiments that our method not only outperforms the RL algorithms without pretraining process, but also is more simulation efficient.