Learning to soar: Resource-constrained exploration in reinforcement learning

This paper examines temporal difference reinforcement learning with adaptive and directed exploration for resourcelimited missions. The scenario considered is that of an unpowered aerial glider learning to perform energy-gaining flight trajectories in a thermal updraft. The presented algorithm, eGP-SARSA(l), uses a Gaussian process regression model to estimate the value function in a reinforcement learning framework. The Gaussian process also provides a variance on these estimates that is used to measure the contribution of future observations to the Gaussian process value function model in terms of information gain. To avoid myopic exploration we developed a resource-weighted objective function that combines an estimate of the future information gain using an action rollout with the estimated value function to generate directed explorative action sequences. A number of modifications and computational speed-ups to the algorithm are presented along with a standard GP-SARSA(l) implementation with e-greedy exploration to compare the respective learning performances. The results show that under this objective function, the learning agent is able to continue exploring for better state-action trajectories when platform energy is high and follow conservative energy-gaining trajectories when platform energy is low.