Results 1  10
of
94
LeastSquares Policy Iteration
 JOURNAL OF MACHINE LEARNING RESEARCH
, 2003
"... We propose a new approach to reinforcement learning for control problems which combines valuefunction approximation with linear architectures and approximate policy iteration. This new approach ..."
Abstract

Cited by 461 (12 self)
 Add to MetaCart
(Show Context)
We propose a new approach to reinforcement learning for control problems which combines valuefunction approximation with linear architectures and approximate policy iteration. This new approach
Multiagent Planning with Factored MDPs
 In NIPS14
, 2001
"... We present a principled and efficient planning algorithm for cooperative multiagent dynamic systems. A striking feature of our method is that the coordination and communication between the agents is not imposed, but derived directly from the system dynamics and function approximation architecture ..."
Abstract

Cited by 174 (15 self)
 Add to MetaCart
(Show Context)
We present a principled and efficient planning algorithm for cooperative multiagent dynamic systems. A striking feature of our method is that the coordination and communication between the agents is not imposed, but derived directly from the system dynamics and function approximation architecture. We view the entire multiagent system as a single, large Markov decision process (MDP), which we assume can be represented in a factored way using a dynamic Bayesian network (DBN). The action space of the resulting MDP is the joint action space of the entire set of agents. Our approach is based on the use of factored linear value functions as an approximation to the joint value function. This factorization of the value function allows the agents to coordinate their actions at runtime using a natural message passing scheme. We provide a simple and efficient method for computing such an approximate value function by solving a single linear program, whose size is determined by the interaction between the value function structure and the DBN. We thereby avoid the exponential blowup in the state and action space. We show that our approach compares favorably with approaches based on reward sharing. We also show that our algorithm is an efficient alternative to more complicated algorithms even in the single agent case.
Efficient Solution Algorithms for Factored MDPs
, 2003
"... 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 re ..."
Abstract

Cited by 174 (4 self)
 Add to MetaCart
(Show Context)
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 MDPs can grow exponentially in the representation size. In this paper, we present two approximate solution algorithms that exploit structure in factored MDPs. Both use an approximate value function represented as a linear combination of basis functions, where each basis function involves only a small subset of the domain variables. A key contribution of this paper is that it shows how the basic operations of both algorithms can be performed efficiently in closed form, by exploiting both additive and contextspecific structure in a factored MDP. A central element of our algorithms is a novel linear program decomposition technique, analogous to variable elimination in Bayesian networks, which reduces an exponentially large LP to a provably equivalent, polynomialsized one. One algorithm uses approximate linear programming, and the second approximate dynamic programming. Our dynamic programming algorithm is novel in that it uses an approximation based on maxnorm, a technique that more directly minimizes the terms that appear in error bounds for approximate MDP algorithms. We provide experimental results on problems with over 10^40 states, demonstrating a promising indication of the scalability of our approach, and compare our algorithm to an existing stateoftheart approach, showing, in some problems, exponential gains in computation time.
Equivalence notions and model minimization in Markov decision processes
, 2003
"... Many stochastic planning problems can be represented using Markov Decision Processes (MDPs). A difficulty with using these MDP representations is that the common algorithms for solving them run in time polynomial in the size of the state space, where this size is extremely large for most realworld ..."
Abstract

Cited by 116 (2 self)
 Add to MetaCart
Many stochastic planning problems can be represented using Markov Decision Processes (MDPs). A difficulty with using these MDP representations is that the common algorithms for solving them run in time polynomial in the size of the state space, where this size is extremely large for most realworld planning problems of interest. Recent AI research has addressed this problem by representing the MDP in a factored form. Factored MDPs, however, are not amenable to traditional solution methods that call for an explicit enumeration of the state space. One familiar way to solve MDP problems with very large state spaces is to form a reduced (or aggregated) MDP with the same properties as the original MDP by combining “equivalent ” states. In this paper, we discuss applying this approach to solving factored MDP problems—we avoid enumerating the state space by describing large blocks of “equivalent” states in factored form, with the block descriptions being inferred directly from the original factored representation. The resulting reduced MDP may have exponentially fewer states than the original factored MDP, and can then be solved using traditional methods. The reduced MDP found depends on the notion of equivalence between states used in the aggregation. The notion of equivalence chosen will be fundamental in designing and analyzing
Protovalue functions: A laplacian framework for learning representation and control in markov decision processes
 Journal of Machine Learning Research
, 2006
"... This paper introduces a novel spectral framework for solving Markov decision processes (MDPs) by jointly learning representations and optimal policies. The major components of the framework described in this paper include: (i) A general scheme for constructing representations or basis functions by d ..."
Abstract

Cited by 92 (11 self)
 Add to MetaCart
(Show Context)
This paper introduces a novel spectral framework for solving Markov decision processes (MDPs) by jointly learning representations and optimal policies. The major components of the framework described in this paper include: (i) A general scheme for constructing representations or basis functions by diagonalizing symmetric diffusion operators (ii) A specific instantiation of this approach where global basis functions called protovalue functions (PVFs) are formed using the eigenvectors of the graph Laplacian on an undirected graph formed from state transitions induced by the MDP (iii) A threephased procedure called representation policy iteration comprising of a sample collection phase, a representation learning phase that constructs basis functions from samples, and a final parameter estimation phase that determines an (approximately) optimal policy within the (linear) subspace spanned by the (current) basis functions. (iv) A specific instantiation of the RPI framework using leastsquares policy iteration (LSPI) as the parameter estimation method (v) Several strategies for scaling the proposed approach to large discrete and continuous state spaces, including the Nyström extension for outofsample interpolation of eigenfunctions, and the use of Kronecker sum factorization to construct compact eigenfunctions in product spaces such as factored MDPs (vi) Finally, a series of illustrative discrete and continuous control tasks, which both illustrate the concepts and provide a benchmark for evaluating the proposed approach. Many challenges remain to be addressed in scaling the proposed framework to large MDPs, and several elaboration of the proposed framework are briefly summarized at the end.
Exploiting Structure to Efficiently Solve Large Scale Partially Observable Markov Decision Processes
, 2005
"... Partially observable Markov decision processes (POMDPs) provide a natural and principled framework to model a wide range of sequential decision making problems under uncertainty. To date, the use of POMDPs in realworld problems has been limited by the poor scalability of existing solution algorithm ..."
Abstract

Cited by 91 (6 self)
 Add to MetaCart
Partially observable Markov decision processes (POMDPs) provide a natural and principled framework to model a wide range of sequential decision making problems under uncertainty. To date, the use of POMDPs in realworld problems has been limited by the poor scalability of existing solution algorithms, which can only solve problems with up to ten thousand states. In fact, the complexity of finding an optimal policy for a finitehorizon discrete POMDP is PSPACEcomplete. In practice, two important sources of intractability plague most solution algorithms: large policy spaces and large state spaces. On the other hand,
Error Bounds for Approximate Policy Iteration
"... In Dynamic Programming, convergence of algorithms such as Value Iteration or Policy Iteration results in discounted problems from a contraction property of the backup operator, guaranteeing convergence to its xedpoint. ..."
Abstract

Cited by 86 (10 self)
 Add to MetaCart
In Dynamic Programming, convergence of algorithms such as Value Iteration or Policy Iteration results in discounted problems from a contraction property of the backup operator, guaranteeing convergence to its xedpoint.
Maxnorm Projections for Factored MDPs
 In IJCAI
, 2001
"... Markov Decision Processes (MDPs) provide a coherent mathematical framework for planning under uncertainty. ..."
Abstract

Cited by 78 (10 self)
 Add to MetaCart
Markov Decision Processes (MDPs) provide a coherent mathematical framework for planning under uncertainty.
Contingent Planning Under Uncertainty via Stochastic Satisfiability
 Artificial Intelligence
, 1999
"... We describe two new probabilistic planning techniques cmaxplan and zanderthat generate contingent plans in probabilistic propositional domains. Both operate by transforming the planning problem into a stochastic satisfiability problem and solving that problem instead. cmaxplan encodes t ..."
Abstract

Cited by 70 (11 self)
 Add to MetaCart
(Show Context)
We describe two new probabilistic planning techniques cmaxplan and zanderthat generate contingent plans in probabilistic propositional domains. Both operate by transforming the planning problem into a stochastic satisfiability problem and solving that problem instead. cmaxplan encodes the problem as an EMajsat instance, while zander encodes the problem as an SSat instance. Although SSat problems are in a higher complexity class than EMajsat problems, the problem encodings produced by zander are substantially more compact and appear to be easier to solve than the corresponding EMajsat encodings. Preliminary results for zander indicate that it is competitive with existing planners on a variety of problems. Introduction When planning under uncertainty, any information about the state of the world is precious. A contingent plan is one that can make action choices contingent on such information. In this paper, we present an implemented framework for contingent pl...
Planning by Probabilistic Inference
 Proc. of the 9th Int. Workshop on Artificial Intelligence and Statistics
, 2003
"... This paper presents and demonstrates a new approach to the problem of planning under uncertainty. Actions are treated as hidden variables, with their own prior distributions, in a probabilistic generative model involving actions and states. Planning is done by computing the posterior distribut ..."
Abstract

Cited by 52 (1 self)
 Add to MetaCart
This paper presents and demonstrates a new approach to the problem of planning under uncertainty. Actions are treated as hidden variables, with their own prior distributions, in a probabilistic generative model involving actions and states. Planning is done by computing the posterior distribution over actions, conditioned on reaching the goal state within a specified number of steps. Under the new formulation, the toolbox of inference techniques be brought to bear on the planning problem. This paper focuses on problems with discrete actions and states, and discusses some extensions.