Results 1  10
of
196
Reinforcement learning: a survey
 Journal of Artificial Intelligence Research
, 1996
"... This paper surveys the field of reinforcement learning from a computerscience perspective. It is written to be accessible to researchers familiar with machine learning. Both the historical basis of the field and a broad selection of current work are summarized. Reinforcement learning is the problem ..."
Abstract

Cited by 1297 (22 self)
 Add to MetaCart
This paper surveys the field of reinforcement learning from a computerscience perspective. It is written to be accessible to researchers familiar with machine learning. Both the historical basis of the field and a broad selection of current work are summarized. Reinforcement learning is the problem faced by an agent that learns behavior through trialanderror interactions with a dynamic environment. The work described here has a resemblance to work in psychology, but differs considerably in the details and in the use of the word "reinforcement." The paper discusses central issues of reinforcement learning, including trading off exploration and exploitation, establishing the foundations of the field via Markov decision theory, learning from delayed reinforcement, constructing empirical models to accelerate learning, making use of generalization and hierarchy, and coping with hidden state. It concludes with a survey of some implemented systems and an assessment of the practical utility of current methods for reinforcement learning.
Generalization in Reinforcement Learning: Successful Examples Using Sparse Coarse Coding
 Advances in Neural Information Processing Systems 8
, 1996
"... On large problems, reinforcement learning systems must use parameterized function approximators such as neural networks in order to generalize between similar situations and actions. In these cases there are no strong theoretical results on the accuracy of convergence, and computational results have ..."
Abstract

Cited by 353 (18 self)
 Add to MetaCart
On large problems, reinforcement learning systems must use parameterized function approximators such as neural networks in order to generalize between similar situations and actions. In these cases there are no strong theoretical results on the accuracy of convergence, and computational results have been mixed. In particular, Boyan and Moore reported at last year's meeting a series of negative results in attempting to apply dynamic programming together with function approximation to simple control problems with continuous state spaces. In this paper, we present positive results for all the control tasks they attempted, and for one that is significantly larger. The most important differences are that we used sparsecoarsecoded function approximators (CMACs) whereas they used mostly global function approximators, and that we learned online whereas they learned offline. Boyan and Moore and others have suggested that the problems they encountered could be solved by using actual outcomes (...
An analysis of temporaldifference learning with function approximation
 IEEE Transactions on Automatic Control
, 1997
"... We discuss the temporaldifference learning algorithm, as applied to approximating the costtogo function of an infinitehorizon discounted Markov chain. The algorithm weanalyze updates parameters of a linear function approximator online, duringasingle endless trajectory of an irreducible aperiodi ..."
Abstract

Cited by 216 (7 self)
 Add to MetaCart
We discuss the temporaldifference learning algorithm, as applied to approximating the costtogo function of an infinitehorizon discounted Markov chain. The algorithm weanalyze updates parameters of a linear function approximator online, duringasingle endless trajectory of an irreducible aperiodic Markov chain with a finite or infinite state space. We present a proof of convergence (with probability 1), a characterization of the limit of convergence, and a bound on the resulting approximation error. Furthermore, our analysis is based on a new line of reasoning that provides new intuition about the dynamics of temporaldifference learning. In addition to proving new and stronger positive results than those previously available, we identify the significance of online updating and potential hazards associated with the use of nonlinear function approximators. First, we prove that divergence may occur when updates are not based on trajectories of the Markov chain. This fact reconciles positive and negative results that have been discussed in the literature, regarding the soundness of temporaldifference learning. Second, we present anexample illustrating the possibility of divergence when temporaldifference learning is used in the presence of a nonlinear function approximator.
Stable Function Approximation in Dynamic Programming
 IN MACHINE LEARNING: PROCEEDINGS OF THE TWELFTH INTERNATIONAL CONFERENCE
, 1995
"... The success of reinforcement learning in practical problems depends on the ability tocombine function approximation with temporal difference methods such as value iteration. Experiments in this area have produced mixed results; there have been both notable successes and notable disappointments. Theo ..."
Abstract

Cited by 206 (5 self)
 Add to MetaCart
The success of reinforcement learning in practical problems depends on the ability tocombine function approximation with temporal difference methods such as value iteration. Experiments in this area have produced mixed results; there have been both notable successes and notable disappointments. Theory has been scarce, mostly due to the difficulty of reasoning about function approximators that generalize beyond the observed data. We provide a proof of convergence for a wide class of temporal difference methods involving function approximators such as knearestneighbor, and show experimentally that these methods can be useful. The proof is based on a view of function approximators as expansion or contraction mappings. In addition, we present a novel view of approximate value iteration: an approximate algorithm for one environment turns out to be an exact algorithm for a different environment.
Algorithms for Sequential Decision Making
, 1996
"... Sequential decision making is a fundamental task faced by any intelligent agent in an extended interaction with its environment; it is the act of answering the question "What should I do now?" In this thesis, I show how to answer this question when "now" is one of a finite set of states, "do" is one ..."
Abstract

Cited by 175 (8 self)
 Add to MetaCart
Sequential decision making is a fundamental task faced by any intelligent agent in an extended interaction with its environment; it is the act of answering the question "What should I do now?" In this thesis, I show how to answer this question when "now" is one of a finite set of states, "do" is one of a finite set of actions, "should" is maximize a longrun measure of reward, and "I" is an automated planning or learning system (agent). In particular,
Stochastic Dynamic Programming with Factored Representations
, 1997
"... Markov decision processes(MDPs) have proven to be popular models for decisiontheoretic planning, but standard dynamic programming algorithms for solving MDPs rely on explicit, statebased specifications and computations. To alleviate the combinatorial problems associated with such methods, we propo ..."
Abstract

Cited by 145 (10 self)
 Add to MetaCart
Markov decision processes(MDPs) have proven to be popular models for decisiontheoretic planning, but standard dynamic programming algorithms for solving MDPs rely on explicit, statebased specifications and computations. To alleviate the combinatorial problems associated with such methods, we propose new representational and computational techniques for MDPs that exploit certain types of problem structure. We use dynamic Bayesian networks (with decision trees representing the local families of conditional probability distributions) to represent stochastic actions in an MDP, together with a decisiontree representation of rewards. Based on this representation, we develop versions of standard dynamic programming algorithms that directly manipulate decisiontree representations of policies and value functions. This generally obviates the need for statebystate computation, aggregating states at the leaves of these trees and requiring computations only for each aggregate state. The key to these algorithms is a decisiontheoretic generalization of classic regression analysis, in which we determine the features relevant to predicting expected value. We demonstrate the method empirically on several planning problems,
Treebased batch mode reinforcement learning
 Journal of Machine Learning Research
, 2005
"... Reinforcement learning aims to determine an optimal control policy from interaction with a system or from observations gathered from a system. In batch mode, it can be achieved by approximating the socalled Qfunction based on a set of fourtuples (xt,ut,rt,xt+1) where xt denotes the system state a ..."
Abstract

Cited by 134 (28 self)
 Add to MetaCart
Reinforcement learning aims to determine an optimal control policy from interaction with a system or from observations gathered from a system. In batch mode, it can be achieved by approximating the socalled Qfunction based on a set of fourtuples (xt,ut,rt,xt+1) where xt denotes the system state at time t, ut the control action taken, rt the instantaneous reward obtained and xt+1 the successor state of the system, and by determining the control policy from this Qfunction. The Qfunction approximation may be obtained from the limit of a sequence of (batch mode) supervised learning problems. Within this framework we describe the use of several classical treebased supervised learning methods (CART, Kdtree, tree bagging) and two newly proposed ensemble algorithms, namely extremely and totally randomized trees. We study their performances on several examples and find that the ensemble methods based on regression trees perform well in extracting relevant information about the optimal control policy from sets of fourtuples. In particular, the totally randomized trees give good results while ensuring the convergence of the sequence, whereas by relaxing the convergence constraint even better accuracy results are provided by the extremely randomized trees.
Valuefunction approximations for partially observable Markov decision processes
 Journal of Artificial Intelligence Research
, 2000
"... Partially observable Markov decision processes (POMDPs) provide an elegant mathematical framework for modeling complex decision and planning problems in stochastic domains in which states of the system are observable only indirectly, via a set of imperfect or noisy observations. The modeling advanta ..."
Abstract

Cited by 127 (0 self)
 Add to MetaCart
Partially observable Markov decision processes (POMDPs) provide an elegant mathematical framework for modeling complex decision and planning problems in stochastic domains in which states of the system are observable only indirectly, via a set of imperfect or noisy observations. The modeling advantage of POMDPs, however, comes at a price — exact methods for solving them are computationally very expensive and thus applicable in practice only to very simple problems. We focus on efficient approximation (heuristic) methods that attempt to alleviate the computational problem and trade off accuracy for speed. We have two objectives here. First, we survey various approximation methods, analyze their properties and relations and provide some new insights into their differences. Second, we present a number of new approximation methods and novel refinements of existing techniques. The theoretical results are supported by experiments on a problem from the agent navigation domain. 1.
A Reinforcement Learning Approach to Jobshop Scheduling
 In Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence
, 1995
"... We apply reinforcement learning methods to learn domainspecific heuristics for job shop scheduling. A repairbased scheduler starts with a criticalpath schedule and incrementally repairs constraint violations with the goal of finding a short conflictfree schedule. The temporal difference algorith ..."
Abstract

Cited by 112 (9 self)
 Add to MetaCart
We apply reinforcement learning methods to learn domainspecific heuristics for job shop scheduling. A repairbased scheduler starts with a criticalpath schedule and incrementally repairs constraint violations with the goal of finding a short conflictfree schedule. The temporal difference algorithm TD() is applied to train a neural network to learn a heuristic evaluation function over states. This evaluation function is used by a onestep lookahead search procedure to find good solutions to new scheduling problems. We evaluate this approach on synthetic problems and on problems from a NASA space shuttle payload processing task. The evaluation function is trained on problems involving a small number of jobs and then tested on larger problems. The TD scheduler performs better than the best known existing algorithm for this taskZweben's iterative repair method based on simulated annealing. The results suggest that reinforcement learning can provide a new method for constructing high...
Convergence Results for SingleStep OnPolicy ReinforcementLearning Algorithms
 MACHINE LEARNING
, 1998
"... An important application of reinforcement learning (RL) is to finitestate control problems and one of the most difficult problems in learning for control is balancing the exploration/exploitation tradeoff. Existing theoretical results for RL give very little guidance on reasonable ways to perform e ..."
Abstract

Cited by 111 (7 self)
 Add to MetaCart
An important application of reinforcement learning (RL) is to finitestate control problems and one of the most difficult problems in learning for control is balancing the exploration/exploitation tradeoff. Existing theoretical results for RL give very little guidance on reasonable ways to perform exploration. In this paper, we examine the convergence of singlestep onpolicy RL algorithms for control. Onpolicy algorithms cannot separate exploration from learning and therefore must confront the exploration problem directly. We prove convergence results for several related onpolicy algorithms with both decaying exploration and persistent exploration. We also provide examples of exploration strategies that can be followed during learning that result in convergence to both optimal values and optimal policies.