-
A User's Guide to Calibrating Robotics Simulators
Simulators are a critical component of modern robotics research. Strateg...
11/17/2020 ∙ by Bhairav Mehta, et al. ∙
5
∙
share
read it
-
Integrated Benchmarking and Design for Reproducible and Accessible Evaluation of Robotic Agents
As robotics matures and increases in complexity, it is more necessary th...
09/09/2020 ∙ by Jacopo Tani, et al. ∙
0
∙
share
read it
-
Curriculum in Gradient-Based Meta-Reinforcement Learning
Gradient-based meta-learners such as Model-Agnostic Meta-Learning (MAML)...
02/19/2020 ∙ by Bhairav Mehta, et al. ∙
18
∙
share
read it
-
Generating Automatic Curricula via Self-Supervised Active Domain Randomization
Goal-directed Reinforcement Learning (RL) traditionally considers an age...
02/18/2020 ∙ by Sharath Chandra Raparthy, et al. ∙
15
∙
share
read it
-
Active Domain Randomization
Domain randomization is a popular technique for improving domain transfe...
04/09/2019 ∙ by Bhairav Mehta, et al. ∙
0
∙
share
read it
-
The AI Driving Olympics at NeurIPS 2018
Despite recent breakthroughs, the ability of deep learning and reinforce...
03/06/2019 ∙ by Julian Zilly, et al. ∙
0
∙
share
read it
-
A Scalable, Flexible Augmentation of the Student Education Process
We present a novel intelligent tutoring system which builds upon well-es...
10/17/2018 ∙ by Bhairav Mehta, et al. ∙
0
∙
share
read it
Bhairav Mehta
is this you? claim profile
∙
0
followers
Université de Montréal
∙
Montréal Institute of Learning Algorithms
