Results 1  10
of
121
Reinforcement Learning I: Introduction
, 1998
"... In which we try to give a basic intuitive sense of what reinforcement learning is and how it differs and relates to other fields, e.g., supervised learning and neural networks, genetic algorithms and artificial life, control theory. Intuitively, RL is trial and error (variation and selection, search ..."
Abstract

Cited by 5512 (123 self)
 Add to MetaCart
In which we try to give a basic intuitive sense of what reinforcement learning is and how it differs and relates to other fields, e.g., supervised learning and neural networks, genetic algorithms and artificial life, control theory. Intuitively, RL is trial and error (variation and selection, search) plus learning (association, memory). We argue that RL is the only field that seriously addresses the special features of the problem of learning from interaction to achieve longterm goals.
Robust Monte Carlo Localization for Mobile Robots
, 2001
"... Mobile robot localization is the problem of determining a robot's pose from sensor data. This article presents a family of probabilistic localization algorithms known as Monte Carlo Localization (MCL). MCL algorithms represent a robot's belief by a set of weighted hypotheses (samples), whi ..."
Abstract

Cited by 829 (88 self)
 Add to MetaCart
Mobile robot localization is the problem of determining a robot's pose from sensor data. This article presents a family of probabilistic localization algorithms known as Monte Carlo Localization (MCL). MCL algorithms represent a robot's belief by a set of weighted hypotheses (samples), which approximate the posterior under a common Bayesian formulation of the localization problem. Building on the basic MCL algorithm, this article develops a more robust algorithm called MixtureMCL, which integrates two complimentary ways of generating samples in the estimation. To apply this algorithm to mobile robots equipped with range finders, a kernel density tree is learned that permits fast sampling. Systematic empirical results illustrate the robustness and computational efficiency of the approach.
Locally weighted learning
 ARTIFICIAL INTELLIGENCE REVIEW
, 1997
"... This paper surveys locally weighted learning, a form of lazy learning and memorybased learning, and focuses on locally weighted linear regression. The survey discusses distance functions, smoothing parameters, weighting functions, local model structures, regularization of the estimates and bias, ass ..."
Abstract

Cited by 596 (53 self)
 Add to MetaCart
This paper surveys locally weighted learning, a form of lazy learning and memorybased learning, and focuses on locally weighted linear regression. The survey discusses distance functions, smoothing parameters, weighting functions, local model structures, regularization of the estimates and bias, assessing predictions, handling noisy data and outliers, improving the quality of predictions by tuning t parameters, interference between old and new data, implementing locally weighted learning e ciently, and applications of locally weighted learning. A companion paper surveys how locally weighted learning can be used in robot learning and control.
Efficient Exploration In Reinforcement Learning
, 1992
"... Exploration plays a fundamental role in any active learning system. This study evaluates the role of exploration in active learning and describes several local techniques for exploration in finite, discrete domains, embedded in a reinforcement learning framework (delayed reinforcement). This paper d ..."
Abstract

Cited by 149 (3 self)
 Add to MetaCart
Exploration plays a fundamental role in any active learning system. This study evaluates the role of exploration in active learning and describes several local techniques for exploration in finite, discrete domains, embedded in a reinforcement learning framework (delayed reinforcement). This paper distinguishes between two families of exploration schemes: undirected and directed exploration. While the former family is closely related to random walk exploration, directed exploration techniques memorize explorationspecific knowledge which is used for guiding the exploration search. In many finite deterministic domains, any learning technique based on undirected exploration is inefficient in terms of learning time, i.e. learning time is expected to scale exponentially with the size of the state space (Whitehead, 1991b) . We prove that for all these domains, reinforcement learning using a directed technique can always be performed in polynomial time, demonstrating the important role of e...
Particle Filters for Mobile Robot Localization
, 2001
"... This article describes a family of methods, known as Monte Carlo localization (MCL) (Dellaert at al. 1999b, Fox et al. 1999b). The MCL algorithm is a particle filter combined with probabilistic models of robot perception and motion. Building on this, we will describe a variation of MCL which uses a ..."
Abstract

Cited by 113 (19 self)
 Add to MetaCart
(Show Context)
This article describes a family of methods, known as Monte Carlo localization (MCL) (Dellaert at al. 1999b, Fox et al. 1999b). The MCL algorithm is a particle filter combined with probabilistic models of robot perception and motion. Building on this, we will describe a variation of MCL which uses a different proposal distribution (a mixture distribution) that facilitates fast recovery from global localization failures. As we will see, this proposal distribution has a range of advantages over that used in standard MCL, but it comes at the price that it is more difficult to implement, and it requires an algorithm for sampling poses from sensor measurements, which might be difficult to obtain. Finally, we will present an extension of MCL to cooperative multirobot localization of robots that can perceive each other during localization. All these approaches have been tested thoroughly in practice. Experimental results are provided to demonstrate their relative strengths and weaknesses in practical robot applications.
Lifelong Robot Learning
 Robotics and Autonomous Systems
, 1993
"... . Learning provides a useful tool for the automatic design of autonomous robots. Recent research on learning robot control has predominantly focussed on learning single tasks that were studied in isolation. If robots encounter a multitude of control learning tasks over their entire lifetime, however ..."
Abstract

Cited by 78 (4 self)
 Add to MetaCart
. Learning provides a useful tool for the automatic design of autonomous robots. Recent research on learning robot control has predominantly focussed on learning single tasks that were studied in isolation. If robots encounter a multitude of control learning tasks over their entire lifetime, however, there is an opportunity to transfer knowledge between them. In order to do so, robots may learn the invariants of the individual tasks and environments. This taskindependent knowledge can be employed to bias generalization when learning control, which reduces the need for realworld experimentation. We argue that knowledge transfer is essential if robots are to learn control with moderate learning times in complex scenarios. Two approaches to lifelong robot learning which both capture invariant knowledge about the robot and its environments are presented. Both approaches have been evaluated using a HERO2000 mobile robot. Learning tasks included navigation in unknown indoor environments an...
Issues in Using Function Approximation for Reinforcement Learning
 IN PROCEEDINGS OF THE FOURTH CONNECTIONIST MODELS SUMMER SCHOOL
, 1993
"... ..."