IEICE Technical Committee

Information and Systems-Neurocomputing(Date:2005/03/22)

Presentation

Meta-learning in reinforcement learning with Sequential Monte Carlo

Ryohei WATANABE, Yohei NAKADA, Takashi MATSUMOTO,

[Date]2005/3/22
[Paper #]NC2004-187

A Role of the Asymptotic Equipartition Property in Return Maximization of Reinforcement Learning

Kazunori IWATA, Hideaki SAKAI, Kazushi IKEDA,

[Date]2005/3/22
[Paper #]NC2004-188

Optimization of parameter values in reinforcement learning for a mobile robot by a genetic algorithm

Keiji KAMEI, Masumi ISHIKAWA,

[Date]2005/3/22
[Paper #]NC2004-189

A decomposition method of value functions for efficient reinforcement learning

Atsushi SHIMOTANI, Shinichi MAEDA, Shin ISHII,

[Date]2005/3/22
[Paper #]NC2004-190

An off-policy reinforcement learning method based on a natural policy gradient method

Yutaka NAKAMURA, Shin ISHII,

[Date]2005/3/22
[Paper #]NC2004-191

Natural TD Learning : Efficient Use of TD-error for Natural Policy Gradient Reinforcement Learning with Discounted Rewards

Tetsuro MORIMURA, Eiji UCHIBE, Kenji DOYA,

[Date]2005/3/22
[Paper #]NC2004-192

複写される方へ

,

[Date]2005/3/22
[Paper #]

Notice about photocopying

,

[Date]2005/3/22
[Paper #]

,

[Date]2005/3/22
[Paper #]