Supplementary Materials for " nullnullnullnullnullnullnullnullnull: Monte-Carlo Planning in Continuous Space MDPs with Non-Asymptotic Analysis " A Algorithm Details

Output: action to take a. Parameters: maximum depth H allowed in HOO. L covers all the nodes in T . We start with the concentration property and then the convergence results. To proceed further, we first need to state several definitions that are useful throughout. We reproduce these definitions here for completeness.