Generative Actor-Critic: An Off-policy Algorithm Using the Push-forward Model
This work addresses a domain-specific problem in reinforcement learning for continuous control, offering an incremental improvement over existing methods.
The paper tackled the problem of ineffective exploration and limited performance in continuous control tasks by proposing Generative Actor-Critic (GAC), an off-policy algorithm using a push-forward model, which improved exploration efficiency and asymptotic performance, as evidenced by experiment results showing multi-modality and enhanced stability.
Model-free deep reinforcement learning has achieved great success in many domains, such as video games, recommendation systems and robotic control tasks. In continuous control tasks, widely used policies with Gaussian distributions results in ineffective exploration of environments and limited performance of algorithms in many cases. In this paper, we propose a density-free off-policy algorithm, Generative Actor-Critic(GAC), using the push-forward model to increase the expressiveness of policies, which also includes an entropy-like technique, MMD-entropy regularizer, to balance the exploration and exploitation. Additionnally, we devise an adaptive mechanism to automatically scale this regularizer, which further improves the stability and robustness of GAC. The experiment results show that push-forward policies possess desirable features, such as multi-modality, which can improve the efficiency of exploration and asymptotic performance of algorithms obviously.