Nothing Special   »   [go: up one dir, main page]

×
Please click here if you are not redirected within a few seconds.
Feb 12, 2018 · This can be used to learn multiple polices which are different in terms of such Wasserstein distances by using a Wasserstein regulariser.
Missing: note | Show results with:note
We have introduced the notion of Wasserstein distance regularisation into reinforcement learning as a means to quantitatively compare the trajectories (i.e., ...
In this note we describe an application of Wasserstein distance to Reinforcement Learning. The Wasserstein distance in question is between the distribution ...
Feb 12, 2018 · An application of Wasserstein distance to Reinforcement Learning is described, where changing the sign of the regularisation parameter, ...
Missing: note | Show results with:note
A note on reinforcement learning with Wasserstein distance regularisation, with applications to multipolicy learning. M. Abdullah, A. Pacchiano, ...
Reinforcement Learning with Wasserstein Distance Regularisation, with Applications to Multipolicy Learning. Mohammed Amin Abdullah*, Aldo Pacchiano*, ...
Missing: note | Show results with:note
[D1] Reinforcement Learning with Wasserstein Distance Regularisation, with Applications to Multipolicy Learning. Mohammed Abdullah, Moez Draief and Aldo ...
Abstract:In this note we describe an application of Wasserstein distance to Reinforcement Learning. The Wasserstein distance in question is between the ...
People also ask
Reinforcement Learning with Wasserstein Distance Regularisation, with Applications to Multipolicy Learning. EWRL 2018. Mohammed Amin Abdullah*, Aldo Pacchiano ...
A note on reinforcement learning with Wasserstein distance regularisation, with applications to multipolicy learning. In this note we describe an application ...