Search Results for author: Andrija Petrovic

Found 3 papers, 1 papers with code

Gaussian Conditional Random Fields for Classification

no code implementations25 Sep 2019 Andrija Petrovic, Mladen Nikolic, Milos Jovanovic, Boris Delibasic

The extended method of local variational approximation of sigmoid function is used for solving empirical Bayes in GCRFBCb variant, whereas MAP value of latent variables is the basis for learning and inference in the GCRFBCnb variant.

Classification

MoET: Interpretable and Verifiable Reinforcement Learning via Mixture of Expert Trees

no code implementations25 Sep 2019 Marko Vasic, Andrija Petrovic, Kaiyuan Wang, Mladen Nikolic, Rishabh Singh, Sarfraz Khurshid

We propose MoET, a more expressive, yet still interpretable model based on Mixture of Experts, consisting of a gating function that partitions the state space, and multiple decision tree experts that specialize on different partitions.

Game of Go Imitation Learning +1

MoET: Mixture of Expert Trees and its Application to Verifiable Reinforcement Learning

1 code implementation16 Jun 2019 Marko Vasic, Andrija Petrovic, Kaiyuan Wang, Mladen Nikolic, Rishabh Singh, Sarfraz Khurshid

By training MoET models using an imitation learning procedure on deep RL agents we outperform the previous state-of-the-art technique based on decision trees while preserving the verifiability of the models.

Game of Go Imitation Learning +2

Cannot find the paper you are looking for? You can Submit a new open access paper.