Marcin Andrychowicz
Marcin Andrychowicz

Ingredients for Robotics Research

We’re releasing eight simulated robotics environments and a Baselines implementation of Hindsight Experience Replay, all developed for our research over the past year. We’ve used these environments to train models which work on physical robots. We’re also releasing a set of requests for robotics research.

Generalizing from Simulation

Our latest robotics techniques allow robot controllers, trained entirely in simulation and deployed on physical robots, to react to unplanned changes in the environment as they solve simple tasks. That is, we’ve used these techniques to build closed-loop systems rather than open-loop ones as before. The simulator need not match

Generalizing from Simulation

Our latest robotics techniques allow robot controllers, trained entirely in simulation and deployed on physical robots, to react to unplanned changes in the environment as they solve simple tasks. That is, we’ve used these techniques to build closed-loop systems rather than open-loop ones as before. The simulator need not match

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.

Action Space Noise Parameter Space Noise

*Parameter noise helps algorithms more

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.

Action Space Noise Parameter Space Noise

Parameter