From Supervised to Reinforcement Learning: an Inverse Optimization Approach

We propose a novel method combining elements of supervised- and Q-learning for the control of dynamical systems subject to unknown disturbances. By using the Inverse Optimization framework and in-hindsight information we can derive a causal parametric optimization policy that approximates a non-causal MPC expert. Furthermore, we propose a new...

Safer reinforcement learning for robotics

Reinforcement learning is an active research area in the fields of artificial intelligence and machine learning, with applications in control. The most important feature of reinforcement learning is its ability to learn without prior knowledge about the system. However, in the real world, reinforcement learning actions may lead to serious damage...

Deep Reinforcement Learning - Pretraining actor-critic networks using state representation learning

In control, the objective is to find a mapping from states to actions that steer a system to a desired reference. A controller can be designed by an engineer, typically using some model of the system or it can be learned by an algorithm. Reinforcement Learning (RL) is one such algorithm. In RL, the controller is an agent that interacts with the...