"Log-Likelihood Optimization" · 2 results · Global ETD Search

Results

Showing 1 to 2 of 2 for “"Log-Likelihood Optimization"”.

Learning Gaussisan noise models from high-dimensional sensor data with deep neural networks

Liu, Katherine YMassachusetts Institute of Technology2018

… for real-time covariance estimation. A direct log-likelihood optimization technique is used to train a deep convolutional neural network to predict the covariance matrix of a Gaussian measurement model, given representative data. This method is algorithm-agnostic, and therefore does not require …

mit Repository record for Learning Gaussisan noise models from high-dimensional sensor data with deep neural networks (opens in a new tab)
Adversarial Inverse Reinforcement Learning with Noisy Observations

Shrestha, Sagar2027

… the problem of reward inference as one of log-likelihood optimization that accommodates noisy input. We adopt two techniques from the literature on learning hidden representations in sequential decision tasks and combine them with AIRL to solve this unified optimization problem. Experiments …

usm Repository record for Adversarial Inverse Reinforcement Learning with Noisy Observations (opens in a new tab)