Fourier Policy Gradients

Abstract

We propose a new way of deriving policy gradient updates for reinforcement learning. Our technique, based on Fourier analysis, recasts integrals that arise with expected policy gradients as convolutions and turns them into multiplications. The obtained analytical solutions allow us to capture the low variance benefits of EPG in a broad range of settings. For the critic, we treat trigonometric and radial basis functions, two function families with the universal approximation property. The choice of policy can be almost arbitrary, including mixtures or hybrid continuous-discrete probability distributions. Moreover, we derive a general family of sample-based estimators for stochastic policy gradients, which unifies existing results on sample-based approximation. We believe that this technique has the potential to shape the next generation of policy gradient approaches, powered by analytical results.

References in corpus (6)

• Continuous control with deep reinforcement learning
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Multiple Object Recognition with Visual Attention
• Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
• Learning Continuous Control Policies by Stochastic Value Gradients
• Expected Policy Gradients for Reinforcement Learning

Cited by in corpus (4)

• VIREL: A Variational Inference Framework for Reinforcement Learning
• Reinforcement Learning for Portfolio Management
• Marginal Policy Gradients: A Unified Family of Estimators for Bounded Action Spaces with Applications
• Representation of Reinforcement Learning Policies in Reproducing Kernel Hilbert Spaces