A key challenge in many reinforcement learning problems is delayed rewards, which can significantly slow down learning. Although reward shaping has previously been introduced to accelerate learning by bootstrapping an agent with additional information, this can lead to problems with convergence. We present a novel Bayesian reward shaping framework that augments the reward distribution with prior beliefs that decay with experience. Formally, we prove that under suitable conditions a Markov decision process augmented with our framework is consistent with the optimal policy of the original MDP when using the Q-learning algorithm. However, in general our method integrates seamlessly with any reinforcement learning algorithm that learns a value or action-value function through experience. Experiments are run on a gridworld and a more complex backgammon domain that show that we can learn tasks significantly faster when we specify intuitive priors on the reward distribution.
Published Date: 2018-02-08
Registration: ISSN 2374-3468 (Online) ISSN 2159-5399 (Print)
Copyright: Published by AAAI Press, Palo Alto, California USA Copyright © 2018, Association for the Advancement of Artificial Intelligence All Rights Reserved.