Contextual Exploration Using a Linear Approximation Method Based on Satisficing

no code implementations • 13 Dec 2021 • Akane Minami, Yu Kono, Tatsuji Takahashi

Thus, we propose Linear RS (LinRS), which is a type of satisficing algorithm and a linear extension of risk-sensitive satisficing (RS), for application to a wider range of tasks.

reinforcement-learning Reinforcement Learning +1

Guaranteed satisficing and finite regret: Analysis of a cognitive satisficing value function

no code implementations • 14 Dec 2018 • Akihiro Tamatsukuri, Tatsuji Takahashi

As reinforcement learning algorithms are being applied to increasingly complicated and realistic tasks, it is becoming increasingly difficult to solve such problems within a practical time frame.

reinforcement-learning Reinforcement Learning +1

Bayesian Inference of Self-intention Attributed by Observer

no code implementations • 12 Oct 2018 • Yosuke Fukuchi, Masahiko Osawa, Hiroshi Yamakawa, Tatsuji Takahashi, Michita Imai

Most of agents that learn policy for tasks with reinforcement learning (RL) lack the ability to communicate with people, which makes human-agent collaboration challenging.

Attribute Bayesian Inference +2