Sciweavers

IJON
2006
90views more  IJON 2006»
14 years 9 months ago
Reinforcement learning of a simple control task using the spike response model
In this work, we propose a variation of a direct reinforcement learning algorithm, suitable for usage with spiking neurons based on the spike response model (SRM). The SRM is a bi...
Murilo Saraiva de Queiroz, Roberto Coelho de Berr&...
ECML
2005
Springer
15 years 3 months ago
Towards Finite-Sample Convergence of Direct Reinforcement Learning
Abstract. While direct, model-free reinforcement learning often performs better than model-based approaches in practice, only the latter have yet supported theoretical guarantees f...
Shiau Hong Lim, Gerald DeJong
64
Voted
ICML
1998
IEEE
15 years 10 months ago
An Analysis of Direct Reinforcement Learning in Non-Markovian Domains
Mark D. Pendrith, Michael McGarity