Parameter estimation from behavioral data in reinforcement learning based on long- and short-term intrinsic rewards

○Hiroki Kurashige

Presentation information

Poster

I. Cognitive Science, Computational Theories and AI

[1Pa] Neuroinformatics and Large-scale Simulation

Tue. Aug 1, 2023 4:00 PM - 5:00 PM Poster Room (Exhibition Building)

[1Pa-130] Parameter estimation from behavioral data in reinforcement learning based on long- and short-term intrinsic rewards

○Hiroki Kurashige¹, Ryosuke Yamada¹ (1. Tokai University)

Keywords:REINFORCEMENT LEARNING, BAYESIAN MODELING, INTRINSIC REWARD, NOVELTY

Abstract password authentication.
A password is required to view the full text of the abstract. Please refer to the member site for the password.

https://membership.jnss.org/C00/login

Presentation information

[1Pa] Neuroinformatics and Large-scale Simulation

[1Pa-130] Parameter estimation from behavioral data in reinforcement learning based on long- and short-term intrinsic rewards

Password