Fast Reinforcement Learning Using Asymmetric Probability Density Function

Kosuke Umesako; Masanao Obayashi; Kunikazu Kobayashi

doi:10.11499/sicep.2002.0.171.0

SICE Annual Conference 2002

DOI https://doi.org/10.11499/sicep.2002.0.171.0

会議情報

主催: The Society of Instrument and Control Engineers

共催: IEEE/Industiral Electronic Society, IEEE/Robotics and Automation Society, IEEE/Control System Society

Fast Reinforcement Learning Using Asymmetric Probability Density Function

Kosuke Umesako, Masanao Obayashi, Kunikazu Kobayashi

著者情報

キーワード: reinforcement learning, acceleration of learning, asymmetric probability density function, temporal difference method, stochastic gradient ascent method, neural network

会議録・要旨集フリー

p. 171

詳細

抄録

We propose an asymmetric probability density function (PDF) to select an effective action on reinforcement learning (RL). The proposed method utilizing the information of search direction enables RL to reduce the number of trials. Furthermore, the proposed method can be applied easily to various methods of RL, for example, actor-critic, stochastic gradient ascent method. The performance of our proposed method is demonstrated by computer simulations.

責任著者(Corresponding author)

J-STAGEへの登録はこちら（無料）