Technical Note: \cal Q-Learning
Machine Learning
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Estimation of Distribution Algorithms: A New Tool for Evolutionary Computation
Estimation of Distribution Algorithms: A New Tool for Evolutionary Computation
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Using a Markov network model in a univariate EDA: an empirical cost-benefit analysis
GECCO '05 Proceedings of the 7th annual conference on Genetic and evolutionary computation
Estimation of Distribution Algorithms with Kikuchi Approximations
Evolutionary Computation
Studying XCS/BOA learning in Boolean functions: structure encoding and random Boolean functions
Proceedings of the 8th annual conference on Genetic and evolutionary computation
Fda -a scalable evolutionary algorithm for the optimization of additively decomposed functions
Evolutionary Computation
Use of infeasible individuals in probabilistic model building genetic network programming
Proceedings of the 13th annual conference on Genetic and evolutionary computation
A Markovianity based optimisation algorithm
Genetic Programming and Evolvable Machines
A novel classification learning framework based on estimation of distribution algorithms
International Journal of Computing Science and Mathematics
A survey of multi-objective sequential decision-making
Journal of Artificial Intelligence Research
| Hi-index | 0.00 |
By making use of probabilistic models, (EDAs) can outperform conventional evolutionary computations. In this paper, EDAs are extended to solve reinforcement learning problems which arise naturally in a framework for autonomous agents. In reinforcement learning problems, we have to find out better policies of agents such that the rewards for agents in the future are increased. In general, such a policy can be represented by conditional probabilities of the agents' actions, given the perceptual inputs. In order to estimate such a conditional probability distribution, Conditional Random Fields (CRFs) by Lafferty et al. is newly introduced into EDAs in this paper. The reason for adopting CRFs is that CRFs are able to learn conditional probabilistic distributions from a large amount of input-output data, i.e., episodes in the case of reinforcement learning problems. On the other hand, conventional reinforcement learning algorithms can only learn incrementally. Computer simulations of Probabilistic Transition Problems and Perceptual Aliasing Maze Problems show the effectiveness of EDA-RL.