Reinforcement learning with hidden states
Proceedings of the second international conference on From animals to animats 2 : simulation of adaptive behavior: simulation of adaptive behavior
The evolution of mental models
Advances in genetic programming
Switching and Finite Automata Theory: Computer Science Series
Switching and Finite Automata Theory: Computer Science Series
Learning Policies with External Memory
ICML '99 Proceedings of the Sixteenth International Conference on Machine Learning
An evolutionary approach to quantify internal states needed for the woods problem
ICSAB Proceedings of the seventh international conference on simulation of adaptive behavior on From animals to animats
Reinforcement learning with selective perception and hidden state
Reinforcement learning with selective perception and hidden state
Stochastic local search for POMDP controllers
AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Learning finite-state controllers for partially observable environments
UAI'99 Proceedings of the Fifteenth conference on Uncertainty in artificial intelligence
Evaluating las vegas algorithms: pitfalls and remedies
UAI'98 Proceedings of the Fourteenth conference on Uncertainty in artificial intelligence
A quantitative analysis of memory requirement and generalization performance for robotic tasks
Proceedings of the 9th annual conference on Genetic and evolutionary computation
MuACOsm: a new mutation-based ant colony optimization algorithm for learning finite-state machines
Proceedings of the 15th annual conference on Genetic and evolutionary computation
Hi-index | 0.00 |
Many agent problems in a grid world have a restricted sensory information and motor actions. The environmental conditions need dynamic processing of internal memory. In this paper, we handle the artificial ant problem, an agent task to model ant trail following in a grid world, which is one of the difficult problems that purely reactive systems cannot solve. We provide an evolutionary approach to quantify the amount of memory needed for the agent problem and explore a systematic analysis over the memory usage. We apply two types of memory-based control structures, Koza's genetic programming and finite state machines, to recognize the relevance of internal memory. Statistical significance test based on beta distribution differentiates the characteristics and performances of the two control structures.