ThermalSoaring

A repository to hold our report

Updated 4 years ago

The senior project poster required for Senior Seminar.

Updated 4 years ago

Dynamic programming / Q learning policy - table based and with neural interpolation.

Updated 4 years ago

The final thermal soaring code with all parts integrated

Updated 4 years ago

bayesian-learning
Jupyter Notebook 0 0

From simple Bayesian demos to using GPR and Bayesian parameter estimation on live data from the Piccolo simulator

Updated 4 years ago

Repository for the relay/data crunching between Thermal Identification, Path Decision Making, and the Autopilot.

Updated 4 years ago

RLDraft1a
MATLAB 0 0

Using reinforcement learning to maximize energy gained from thermal.

Updated 4 years ago

May actually be using TD(lambda). Outputs average RMS error of the values of the states in a random walk, using the TD reinforcement learning algorithm. Note that batch learning was NOT used, although it will be in future demos.

Updated 5 years ago

Compares effectiveness of epsilon greedy algorithms as the number of trials increases.

Updated 5 years ago

Learning agent finds its way through a maze to a reward square, using dynamic programming.

Updated 5 years ago

Learning agent learns how to play gambling game using Monte Carlo Simulation.

Updated 5 years ago

People