Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 2 of 2
Full-Text Articles in Engineering
Utilizing Trajectory Optimization In The Training Of Neural Network Controllers, Nicholas Kimball
Utilizing Trajectory Optimization In The Training Of Neural Network Controllers, Nicholas Kimball
Master's Theses
Applying reinforcement learning to control systems enables the use of machine learning to develop elegant and efficient control laws. Coupled with the representational power of neural networks, reinforcement learning algorithms can learn complex policies that can be difficult to emulate using traditional control system design approaches. In this thesis, three different model-free reinforcement learning algorithms, including Monte Carlo Control, REINFORCE with baseline, and Guided Policy Search are compared in simulated, continuous action-space environments. The results show that the Guided Policy Search algorithm is able to learn a desired control policy much faster than the other algorithms. In the inverted pendulum …
Verification Of Stochastic Reach-Avoid Using Rkhs Embeddings, Adam J. Thorpe
Verification Of Stochastic Reach-Avoid Using Rkhs Embeddings, Adam J. Thorpe
Electrical and Computer Engineering ETDs
A solution to the terminal-hitting and first-hitting stochastic reach-avoid problem for a Markov control process is presented. This solution takes advantage of a nonparametric representation of the stochastic kernel as a conditional distribution embedding within a reproducing kernel Hilbert space (RKHS). Because the disturbance is modeled as a data-driven stochastic process, this representation avoids intractable integrals in the dynamic recursion of the reach-avoid problem since the expectations can be calculated as an inner product within the RKHS. An example using a high-dimensional chain of integrators is presented, as well as for Clohessy-Wiltshire-Hill (CWH) dynamics.