Search Results for author:
Found 5 papers, 1 papers with code
Distilled Domain Randomization
However, these methods are notorious for the enormous amount of required training data which is prohibitively expensive to collect on real robots.
Robot Learning from Randomized Simulations: A Review
The rise of deep learning has caused a paradigm shift in robotics research, favoring methods that require large amounts of data.
An Empirical Analysis of Measure-Valued Derivatives for Policy Gradients
This estimator is unbiased, has low variance, and can be used with differentiable and non-differentiable function approximators.
Data-efficient Domain Randomization with Bayesian Optimization
Domain randomization methods tackle this problem by randomizing the physics simulator (source domain) during training according to a distribution over domain parameters in order to obtain more robust policies that are able to overcome the reality gap.
Assessing Transferability from Simulation to Reality for Reinforcement Learning
Optimizing a policy on a slightly faulty simulator can easily lead to the maximization of the `Simulation Optimization Bias` (SOB).
