Angrier Birds: Bayesian reinforcement learning

01/06/2016
by   Imanol Arrieta Ibarra, et al.
0

We train a reinforcement learner to play a simplified version of the game Angry Birds. The learner is provided with a game state in a manner similar to the output that could be produced by computer vision algorithms. We improve on the efficiency of regular ϵ-greedy Q-Learning with linear function approximation through more systematic exploration in Randomized Least Squares Value Iteration (RLSVI), an algorithm that samples its policy from a posterior distribution on optimal policies. With larger state-action spaces, efficient exploration becomes increasingly important, as evidenced by the faster learning in RLSVI.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset