Learning Factored Representations for Partially Observable Markov Decision Processes

The problem of reinforcement learning in a non-Markov environment is explored using a dynamic Bayesian network, where conditional independence assumptionsbetween random variables are compactly represented by network parameters. The parameters are learned online, and approximations areused to perform inference and to compute the optimal value function. The relative effects of inference and value function approximations onthe quality of the final policy are investigated, by learning to solve a moderately difficult driving task. The two value function approximations, linearand quadratic, were found to perform similarly, but the quadratic model was more sensitive to initialization. Both performed below thelevel of human performance on the task.