In English

Reinforcement learning A comparison of learning agents in environments with large discrete state spaces

Johan Andersson ; Emil Kristiansson ; Joakim Persson ; Daniel Toom ; Adam Sandberg Eriksson ; Joppe Widstam
Göteborg : Chalmers tekniska högskola, 2014. 39 s.
[Examensarbete för kandidatexamen]

For some real-world optimization problems where the best behavior is sought, it is infeasible to search for a solution by making a model of the problem and performing calculations on it. When this is the case, good solutions can sometimes be found by trial and error. Reinforcement learning is a way of nding optimal behavior by systematic trial and error. This thesis aims to compare di erent reinforcement learning techniques and evaluate them. Model-based interval estimation (MBIE) and Explicit Explore or Exploit using dynamic bayesian networks (DBN-E3) are two algorithms that are evaluated. To evaluate the techniques, learning agents were constructed using the algorithms and then simulated in the environment Invasive Species from the Reinforcement Learning Competition. The results of the study show that an optimized version of DBN-E3 is better than MBIE at nding an optimal or near optimal behavior policy in Invasive Species for a selection of environment parameters. Using a factored model like a DBN shows certain advantages operating in Invasive Species, which is a factored environment. For example it achieves a near optimal policy within fewer episodes than MBIE.

Nyckelord: Reinforcement learning, Arti cial intelligence, MBIE, DBN-E3, InvasiveSpecies, Learning algorithms



Publikationen registrerades 2014-09-22.

CPL ID: 203119

Detta är en tjänst från Chalmers bibliotek