8 accepted papers
Model-based reinforcement learning is one approach to increase sample efficiency. However, the accuracy of the dynamics model and the resulting compounding error over modelled trajectories are commonly regarded as key limitations. A natural question to ask is: How much more sample efficiency can be…
A limitation of model-based reinforcement learning (MBRL) is the exploitation of errors in the learned models. Blackbox models can fit complex dynamics with high fidelity, but their behavior is undefined outside of the data distribution. Physics-based models are better at extrapolating, due to the g…
When transferring a control policy from simulation to a physical system; this policy needs to be robust to variations in the dynamics to perform well. Commonly; the optimal policy overfits to the approximate model and the corresponding state-distribution. Therefore; the policy fails when transferred…
Classical value iteration approaches are not applicable to environments with continuous states and actions. For such environments the states and actions must be discretized, which leads to an exponential increase in computational complexity. In this paper, we propose continuous fitted value iteratio…
Robots that can learn in the physical world will be important to enable robots to escape their stiff and pre-programmed movements. For dynamic high-acceleration tasks, such as juggling, learning in the real-world is particularly challenging as one must push the limits of the robot and its actuation
Applying Deep Learning to control has a lot of potential for enabling the intelligent design of robot control laws. Unfortunately common deep learning approaches to control, such as deep reinforcement learning, require an unrealistic amount of interaction with the real system, do not yield any perfo…
Deep learning has achieved astonishing results on many tasks with large amounts of data and generalization within the proximity of training data. For many important real-world applications, these requirements are unfeasible and additional prior knowledge on the task domain is required to overcome th…
Learning optimal feedback control laws capable of executing optimal trajectories is essential for many robotic applications. Such policies can be learned using reinforcement learning or planned using optimal control. While reinforcement learning is sample inefficient, optimal control only plans an o