Timezone: »

 
Oral
Fourier Policy Gradients
Matthew Fellows · Kamil Ciosek · Shimon Whiteson

Fri Jul 13 07:40 AM -- 07:50 AM (PDT) @ A1
in Reinforcement Learning 16 »

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.

[ PDF] 

Author Information

Matthew Fellows (University of Oxford)
Kamil Ciosek (Oxford)
Shimon Whiteson (University of Oxford)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors