Vector quantization and signal compression
Vector quantization and signal compression
Automatic programming of behavior-based robots using reinforcement learning
Artificial Intelligence
Technical Note: \cal Q-Learning
Machine Learning
Message-Based Bucket Brigade: An Algorithm for the Apportionment of Credit Problem
EWSL '91 Proceedings of the European Working Session on Machine Learning
Team-Partitioned, Opaque-Transition Reinforced Learning
RoboCup-98: Robot Soccer World Cup II
Path-Tracking Control of Non-holonomic Car-Like Robot with Reinforcement Learning
RoboCup-99: Robot Soccer World Cup III
IJCAI'99 Proceedings of the 16th international joint conference on Artificial intelligence - Volume 2
Input generalization in delayed reinforcement learning: an algorithm and performance comparisons
IJCAI'91 Proceedings of the 12th international joint conference on Artificial intelligence - Volume 2
Exploiting structure in policy construction
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
Model minimization in Markov decision processes
AAAI'97/IAAI'97 Proceedings of the fourteenth national conference on artificial intelligence and ninth conference on Innovative applications of artificial intelligence
A Reinforcement Learning Algorithm in Cooperative Multi-Robot Domains
Journal of Intelligent and Robotic Systems
From Continuous Behaviour to Discrete Knowledge
IWANN '03 Proceedings of the 7th International Work-Conference on Artificial and Natural Neural Networks: Part II: Artificial Neural Nets Problem Solving Methods
Two Steps Reinforcement Learning in Continuous Reinforcement Learning Tasks
IWANN '09 Proceedings of the 10th International Work-Conference on Artificial Neural Networks: Part I: Bio-Inspired Systems: Computational and Ambient Intelligence
Roboskeleton: An architecture for coordinating robot soccer agents
Engineering Applications of Artificial Intelligence
ICCBR'10 Proceedings of the 18th international conference on Case-Based Reasoning Research and Development
Hi-index | 0.00 |
Reinforcement learning has proven to be a set of successful techniques for finding optimal policies on uncertain and/or dynamic domains, such as the RoboCup. One of the problems on using such techniques appears with large state and action spaces, as it is the case of input information coming from the Robosoccer simulator. In this paper, we describe a new mechanism for solving the states generalization problem in reinforcement learning algorithms. This clustering mechanism is based on the vector quantization technique for signal analog-to-digital conversion and compression, and on the Generalized Lloyd Algorithm for the design of vector quantizers. Furthermore, we present the VQQL model, that integrates Q-Learning as reinforcement learning technique and vector quantization as state generalization technique. We show some results on applying this model to learning the interception task skill for Robosoccer agents.