Reinforcement learning (RL) algorithms are typically limited to learning...
Learning from noisy demonstrations is a practical but highly challenging...
Model-based reinforcement learning (MBRL) has been applied to meta-learn...
The goal of imitation learning (IL) is to learn a good policy from
high-...
Imitation learning (IL) aims to learn an optimal policy from demonstrati...
Real-world tasks are often highly structured. Hierarchical reinforcement...
Actor-critic methods can achieve incredible performance on difficult
rei...
Recent research has shown that although Reinforcement Learning (RL) can
...
Uncertainty computation in deep learning is essential to design robust a...
Many computationally-efficient methods for Bayesian deep learning rely o...
We present the Variational Adaptive Newton (VAN) method which is a black...
Many reinforcement learning methods for continuous control tasks are bas...
Direct contextual policy search methods learn to improve policy paramete...
A typical goal of supervised dimension reduction is to find a low-dimens...
Regression aims at estimating the conditional mean of output given input...
The goal of reinforcement learning (RL) is to let an agent learn an opti...
The policy gradient approach is a flexible and powerful reinforcement
le...