Results 1  10
of
144
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 1405 (23 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.
DecisionTheoretic Planning: Structural Assumptions and Computational Leverage
 JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH
, 1999
"... Planning under uncertainty is a central problem in the study of automated sequential decision making, and has been addressed by researchers in many different fields, including AI planning, decision analysis, operations research, control theory and economics. While the assumptions and perspectives ..."
Abstract

Cited by 443 (4 self)
 Add to MetaCart
Planning under uncertainty is a central problem in the study of automated sequential decision making, and has been addressed by researchers in many different fields, including AI planning, decision analysis, operations research, control theory and economics. While the assumptions and perspectives adopted in these areas often differ in substantial ways, many planning problems of interest to researchers in these fields can be modeled as Markov decision processes (MDPs) and analyzed using the techniques of decision theory. This paper presents an overview and synthesis of MDPrelated methods, showing how they provide a unifying framework for modeling many classes of planning problems studied in AI. It also describes structural properties of MDPs that, when exhibited by particular classes of problems, can be exploited in the construction of optimal or approximately optimal policies or plans. Planning problems commonly possess structure in the reward and value functions used to de...
Using Temporal Logics to Express Search Control Knowledge for Planning
 ARTIFICIAL INTELLIGENCE
, 1999
"... Over the years increasingly sophisticated planning algorithms have been developed. These have made for more efficient planners, but unfortunately these planners still suffer from combinatorial complexity even in simple domains. Theoretical results demonstrate that planning is in the worst case in ..."
Abstract

Cited by 297 (14 self)
 Add to MetaCart
Over the years increasingly sophisticated planning algorithms have been developed. These have made for more efficient planners, but unfortunately these planners still suffer from combinatorial complexity even in simple domains. Theoretical results demonstrate that planning is in the worst case intractable. Nevertheless, planning in particular domains can often be made tractable by utilizing additional domain structure. In fact, it has long been acknowledged that domain independent planners need domain dependent information to help them plan effectively. In this
Acting Optimally in Partially Observable Stochastic Domains
, 1994
"... In this paper, we describe the partially observable Markov decision process (pomdp) approach to finding optimal or nearoptimal control strategies for partially observable stochastic environments, given a complete model of the environment. The pomdp approach was originally developed in the oper ..."
Abstract

Cited by 290 (16 self)
 Add to MetaCart
In this paper, we describe the partially observable Markov decision process (pomdp) approach to finding optimal or nearoptimal control strategies for partially observable stochastic environments, given a complete model of the environment. The pomdp approach was originally developed in the operations research community and provides a formal basis for planning problems that have been of interest to the AI community. We found the existing algorithms for computing optimal control strategies to be highly computationally inefficient and have developed a new algorithm that is empirically more efficient. We sketch this algorithm and present preliminary results on several small problems that illustrate important properties of the pomdp approach.
An Algorithm for Probabilistic Planning
, 1995
"... We define the probabilistic planning problem in terms of a probability distribution over initial world states, a boolean combination of propositions representing the goal, a probability threshold, and actions whose effects depend on the executiontime state of the world and on random chance. Adoptin ..."
Abstract

Cited by 277 (19 self)
 Add to MetaCart
We define the probabilistic planning problem in terms of a probability distribution over initial world states, a boolean combination of propositions representing the goal, a probability threshold, and actions whose effects depend on the executiontime state of the world and on random chance. Adopting a probabilistic model complicates the definition of plan success: instead of demanding a plan that provably achieves the goal, we seek plans whose probability of success exceeds the threshold. In this paper, we present buridan, an implemented leastcommitment planner that solves problems of this form. We prove that the algorithm is both sound and complete. We then explore buridan's efficiency by contrasting four algorithms for plan evaluation, using a combination of analytic methods and empirical experiments. We also describe the interplay between generating plans and evaluating them, and discuss the role of search control in probabilistic planning. 3 We gratefully acknowledge the comment...
Probabilistic robot navigation in partially observable environments
 In Proc. of the International Joint Conference on Artificial Intelligence (IJCAI
, 1995
"... Autonomous mobile robots need very reliable navigation capabilities in order to operate unattended for long periods of time. This paper reports on first results of a research program that uses partially observable Markov models to robustly track a robot’s location in office environments and to direc ..."
Abstract

Cited by 263 (11 self)
 Add to MetaCart
Autonomous mobile robots need very reliable navigation capabilities in order to operate unattended for long periods of time. This paper reports on first results of a research program that uses partially observable Markov models to robustly track a robot’s location in office environments and to direct its goaloriented actions. The approach explicitly maintains a probability distribution over the possible locations of the robot, taking into account various sources of uncertainty, including approximate knowledge of the environment, and actuator and sensor uncertainty. A novel feature of our approach is its integration of topological map information with approximate metric information. We demonstrate the robustness of this approach in controlling an actual indoor mobile robot navigating corridors. 1
Exploiting structure in policy construction
 IJCAI95, pp.1104–1111
, 1995
"... Markov decision processes (MDPs) have recently been applied to the problem of modeling decisiontheoretic planning. While traditional methods for solving MDPs are often practical for small states spaces, their effectiveness for large AI planning problems is questionable. We present an algorithm, call ..."
Abstract

Cited by 231 (22 self)
 Add to MetaCart
Markov decision processes (MDPs) have recently been applied to the problem of modeling decisiontheoretic planning. While traditional methods for solving MDPs are often practical for small states spaces, their effectiveness for large AI planning problems is questionable. We present an algorithm, called structured policy iteration (SPI), that constructs optimal policies without explicit enumeration of the state space. The algorithm retains the fundamental computational steps of the commonly used modified policy iteration algorithm, but exploitsthe variable and propositionalindependencies reflected in a temporal Bayesian network representation of MDPs. The principles behind SPI can be applied to any structured representation of stochastic actions, policies and value functions, and the algorithm itself can be used in conjunction with recent approximation methods. 1
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 158 (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,
Planning for Temporally Extended Goals
, 1997
"... this paper appears in Proceedings of AAAI '96, pp. 12151222. F. Bacchus and F. Kabanza / Temporally Extended Goals 2 Yet this flexibility also poses a problem: how do we communicate to such an agent the task we want accomplished in a sufficiently precise manner so that it does what we really ..."
Abstract

Cited by 146 (10 self)
 Add to MetaCart
this paper appears in Proceedings of AAAI '96, pp. 12151222. F. Bacchus and F. Kabanza / Temporally Extended Goals 2 Yet this flexibility also poses a problem: how do we communicate to such an agent the task we want accomplished in a sufficiently precise manner so that it does what we really
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 136 (4 self)
 Add to MetaCart
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.