Richard Chen

4 posts

Learning Montezuma's Revenge from a Single Demonstration

Evolved Policy Gradients

Learning to Model Other Minds

Better Exploration with Parameter Noise

Better Exploration with Parameter Noise

We've found that adding adaptive noise to the parameters of reinforcement learning algorithms frequently boosts performance. This exploration method is simple to implement and very rarely decreases performance, so it's worth trying on any problem.


4 minute read