Automation is increasingly at the forefront of transportation research, with the potential to
bring fully autonomous vehicles to our roads in the coming years. This comprehensive …

The last five years marked a surge in interest for and use of smart robots, which operate in
dynamic and unstructured environments and might interact with humans. We posit that well …

Abstract Model-based reinforcement learning (RL) algorithms can attain excellent sample
efficiency, but often lag behind the best model-free algorithms in terms of asymptotic …

We investigate whether a robot arm can learn to pick and throw arbitrary rigid objects into
selected boxes quickly and accurately. Throwing has the potential to increase the physical …

Bridging thereality gap'that separates simulated robotics from experiments on hardware
could accelerate robotic research through improved data availability. This paper explores …

We present foundations for using Model Predictive Control (MPC) as a differentiable policy
class for reinforcement learning. This provides one way of leveraging and combining the …

Model-free reinforcement learning (RL) methods are succeeding in a growing number of
tasks, aided by recent advances in deep learning. However, they tend to suffer from high …

Reinforcement learning is an appealing approach for allowing robots to learn new tasks.
Relevant literature reveals a plethora of methods, but at the same time makes clear the lack …

We present a unified framework for learning continuous control policies
usingbackpropagation. It supports stochastic control by treating stochasticity in theBellman …

Sample complexity and safety are major challenges when learning policies with
reinforcement learning for real-world tasks, especially when the policies are represented …