3 papers
cs.LG2025
Neural Risk-sensitive Satisficing in Contextual Bandits
Shogo Ito, Tatsuji Takahashi, Yu Kono
The contextual bandit problem, which is a type of reinforcement learning tasks, provides an effective framework for solving challenges in recommendation systems, such as satisfying…
cs.LG2024
Reinforcement Learning with a Focus on Adjusting Policies to Reach Targets
Akane Tsuboya, Yu Kono, Tatsuji Takahashi
The objective of a reinforcement learning agent is to discover better actions through exploration. However, typical exploration techniques aim to maximize rewards, often incurring…
cs.LG2021
Contextual Exploration Using a Linear Approximation Method Based on Satisficing
Akane Minami, Yu Kono, Tatsuji Takahashi
Deep reinforcement learning has enabled human-level or even super-human performance in various types of games. However, the amount of exploration required for learning is often qui…