A key element in the solution of reinforcement learning problems is the value function. The purpose of this function is to measure the long-term utility or value of any given state and it is important because an agent can use it to decide what to do next. A common problem in reinforcement learning when applied to systems having continuous states and action… (More)
Case-based reasoning systems have traditionallybeen used to perform high-level reasoning in problem domains that can be adequately described using discrete , symbolic representations. However, many real-world problem domains, such as autonomous robotic navigation, are better characterized using continuous representations. Such problem domains also require… (More)
The goal of transfer learning is to use the knowledge acquired in a set of source tasks to improve performance in a related but previously unseen target task. In this paper, we present a multi-layered architecture named CAse-Based Reinforcement Learner (CARL). It uses a novel combination of Case-Based Reasoning (CBR) and Reinforcement Learning (RL) to… (More)
This paper compares direct reinforcement learning (no explicit model) and model-based reinforcement learning on a simple task: pendulum swing up. We nd that in this task model-based approaches support reinforcement learning from smaller amounts of training data and eecient handling of changing goals.
Georgia Tech won the OOce Cleanup Event at the 1994 AAAI Mobile Robot Competition with a multi-robot cooperating team. This paper describes the design and implementation of these reactive trash-collecting robots, including details of multiagent cooperation, color vision for the detection of perceptual object classes, temporal sequencing of behaviors for… (More)
Two important goals in the evaluation of an AI theory or model are to assess the merit of the design decisions in the performance of an implemented computer system and to analyze the impact in the performance when the system faces problem domains with different characteristics. This is particularly difficult in case-based reasoning systems because such… (More)
This paper presents an algorithm that can recognize and localize objects given a model of their contours using only ultrasonic range data. The algorithm exploits a physical model of the ultrasonic beam and combines several readings to extract outline object segments from the environment. It then detects patterns of outline segments that correspond to… (More)
A new polynomial-time cooling schedule. A comparison of direct and model-based reinforcement learning. S. Baluja and S. Davies. Combining multiple optimization runs with optimal dependency trees.
This paper describes lessons learned in the design, construction and programming of a team of three reac-tive trash-collecting robots. The robots placed first in the Office Cleanup Event at the 1994 AAAI Mobile Robot Competition. The discussion includes details of multiagent cooperation, color vision for the detection of perceptual object classes, temporal… (More)