Fourier policy gradients
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 lo...
Váldodahkkit: | Fellows, M, Ciosek, K, Whiteson, S |
---|---|
Materiálatiipa: | Conference item |
Almmustuhtton: |
Journal of Machine Learning Research
2018
|
Geahča maid
-
Expected policy gradients
Dahkki: Ciosek, K, et al.
Almmustuhtton: (2018) -
Expected policy gradients for reinforcement learning
Dahkki: Ciosek, K, et al.
Almmustuhtton: (2020) -
OFFER: Off-environment reinforcement learning
Dahkki: Ciosek, K, et al.
Almmustuhtton: (2017) -
Counterfactual multi−agent policy gradients
Dahkki: Foerster, J, et al.
Almmustuhtton: (2018) -
Fast efficient hyperparameter tuning for policy gradient methods
Dahkki: Paul, S, et al.
Almmustuhtton: (2019)