Proceedings of the first international conference on simulation of adaptive behavior on From animals to animats
Technical Note: \cal Q-Learning
Machine Learning
An optimization-based categorization of reinforcement learning environments
Proceedings of the second international conference on From animals to animats 2 : simulation of adaptive behavior: simulation of adaptive behavior
Acting optimally in partially observable stochastic domains
AAAI'94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 2)
Adding temporary memory to ZCS
Adaptive Behavior
Evolutionary Computation
Lookahead And Latent Learning In ZCS
GECCO '02 Proceedings of the Genetic and Evolutionary Computation Conference
An abstraction agorithm for genetics-based reinforcement learning
GECCO '05 Proceedings of the 7th annual conference on Genetic and evolutionary computation
Zcs: A zeroth level classifier system
Evolutionary Computation
Classifier fitness based on accuracy
Evolutionary Computation
A multiagent model of the UK market in electricity generation
IEEE Transactions on Evolutionary Computation
Learning Mazes with Aliasing States: An LCS Algorithm with Associative Perception
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Speedup character-based matching in learning classifier systems with Xor
Proceedings of the 12th annual conference companion on Genetic and evolutionary computation
Learning classifier system with average reward reinforcement learning
Knowledge-Based Systems
Adding memory condition to learning classifier systems to solve partially observable environments
International Journal of Computer Applications in Technology
Hi-index | 0.00 |
Maze problems represent a simplified virtual model of the real environment and can be used for developing core algorithms of many real-world application related to the problem of navigation. Learning Classifier Systems (LCS) are the most widely used class of algorithms for reinforcement learning in mazes. However, LCSs best achievements in maze problems are still mostly bounded to non-aliasing environments, while LCS complexity seems to obstruct a proper analysis of the reasons for failure. Moreover, there is a lack of knowledge of what makes a maze problem hard to solve by a learning agent. To overcome this restriction we try to improve our understanding of the nature and structure of maze environments. In this paper we describe a new LCS agent that has a simpler and more transparent performance mechanism. We use the structure of a predictive LCS model, strip out the evolutionary mechanism, simplify the reinforcement learning procedure and equip the agent with the ability to Associative Perception, adopted from psychology. We then assess the new LCS with Associative Perception on an extensive set of mazes and analyse the results to discover which features of the environments play the most significant role in the learning process. We identify a particularly hard feature for learning in mazes, aliasing clones, which arise when groups of aliasing cells occur in similar patterns in different parts of the maze. We discuss the impact of aliasing clones and other types of aliasing on learning algorithms.