Non-Parametric Approximate Linear Programming for MDPs
نویسندگان
چکیده
The Approximate Linear Programming (ALP) approach to value function approximation for MDPs is a parametric value function approximation method, in that it represents the value function as a linear combination of features which are chosen a priori. Choosing these features can be a difficult challenge in itself. One recent effort, Regularized Approximate Linear Programming (RALP), uses L1 regularization to address this issue by combining a large initial set of features with a regularization penalty that favors a smooth value function with few non-zero weights. Rather than using smoothness as a backhanded way of addressing the feature selection problem, this paper starts with smoothness and develops a non-parametric approach to ALP that is consistent with the smoothness assumption. We show that this new approach has some favorable practical and analytical properties in comparison to (R)ALP.
منابع مشابه
Learning Basis Functions in Hybrid Domains
Markov decision processes (MDPs) with discrete and continuous state and action components can be solved efficiently by hybrid approximate linear programming (HALP). The main idea of the approach is to approximate the optimal value function by a set of basis functions and optimize their weights by linear programming. The quality of this approximation naturally depends on its basis functions. How...
متن کاملEfficient Solution Algorithms for Factored MDPs
This paper addresses the problem of planning under uncertainty in large Markov Decision Processes (MDPs). Factored MDPs represent a complex state space using state variables and the transition model using a dynamic Bayesian network. This representation often allows an exponential reduction in the representation size of structured MDPs, but the complexity of exact solution algorithms for such MD...
متن کاملApproximate Linear Programming for Solving Hybrid Factored MDPs
Hybrid approximate linear programming (HALP) has recently emerged as a promising approach to solving large factored Markov decision processes (MDPs) with discrete and continuous state and action variables. Its central idea is to reformulate initially intractable problem of computing the optimal value function as its linear programming approximation. In this work, we present the HALP framework a...
متن کاملExploiting Anonymity in Approximate Linear Programming: Scaling to Large Multiagent MDPs (Extended Version)
Many exact and approximate solution methods for Markov Decision Processes (MDPs) attempt to exploit structure in the problem and are based on factorization of the value function. Especially multiagent settings, however, are known to suffer from an exponential increase in value component sizes as interactions become denser, meaning that approximation architectures are restricted in the problem s...
متن کاملSymmetric Primal-Dual Approximate Linear Programming for Factored MDPs
A weakness of classical Markov decision processes is that they scale very poorly due to the flat state-space representation. Factored MDPs address this representational problem by exploiting problem structure to specify the transition and reward functions of an MDP in a compact manner. However, in general, solutions to factored MDPs do not retain the structure and compactness of the problem rep...
متن کامل