On the road from Model-Based Dynamical Programming to Model-Free Reinforcement Learning: A sample efficient approach

This thesis introduces a new method, called Mixed Iteration, for controlling Markov Decision Processes when partial information is known about the dynamics of the Markov Decision Process. The algorithm uses sampling to calculate the expectation of partially known dynamics in stochastic environments. Its goal is to lower the number of iterations...

Sample-efficient reinforcement learning for quadcopter flight control

The combination of reinforcement learning and deep neural networks has the potential to train intelligent autonomous agents on high dimensional sensory inputs, with applications in flight control. However, the amount of samples needed by these methods is often too large to use real-world interaction. In this work, mirror-descent guided policy...

Generalized Optimistic Q-Learning with Provable Efficiency

Reinforcement learning (RL), like any on-line learning method, inevitably faces the exploration-exploitation dilemma. When a learning algorithm requires as few data samples as possible, it is called sample efficient. The design of sample-efficient algorithms is an important area of research. Interestingly, all currently known provably efficient...

Hierarchical Reinforcement Learning for Model-Free Flight Control: A sample efficient tabular approach using Q(lambda)-learning and options in a traditional flight control structure

Reinforcement learning (RL) is a model-free adaptive approach to learn a non-linear control law for flight control. However, for flat-RL (FRL) the size of the search space grows exponentially with the number of states, resulting in low sample efficiency. This research aims to improve the efficiency with Hierarchical Reinforcement Learning (HRL)....

Uncertainty reduction and sampling efficiency in slope designs using 3D conditional random fields

A method of combining 3D Kriging for geotechnical sampling schemes with an existing random field generator is presented and validated. Conditional random fields of soil heterogeneity are then linked with finite elements, within a Monte Carlo framework, to investigate optimum sampling locations and the cost-effective design of a slope. The...