83 citations · 151 across the 10 of their papers we have counts for
10 papers
Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying
Soichiro Nishimori, Paavo Parmas, Sotetsu Koyamada +4
In reinforcement learning (RL), agents benefit from exploration only because they repeatedly encounter similar states: trying different actions can improve performance or reduce un…
Mahjax: A GPU-Accelerated Mahjong Simulator for Reinforcement Learning in JAX
Soichiro Nishimori, Shinri Okano, Keigo Habara +3
Riichi Mahjong is a multi-player, imperfect-information game characterized by stochasticity and high-dimensional state spaces. These attributes present a unique combination of chal…
A Simple, Solid, and Reproducible Baseline for Bridge Bidding AI
Haruka Kita, Sotetsu Koyamada, Yotaro Yamaguchi +1
Contract bridge, a cooperative game characterized by imperfect information and multi-agent dynamics, poses significant challenges and serves as a critical benchmark in artificial i…
A Batch Sequential Halving Algorithm without Performance Degradation
Sotetsu Koyamada, Soichiro Nishimori, Shin Ishii
In this paper, we investigate the problem of pure exploration in the context of multi-armed bandits, with a specific focus on scenarios where arms are pulled in fixed-size batches.…
End-to-End Policy Gradient Method for POMDPs and Explainable Agents
Soichiro Nishimori, Sotetsu Koyamada, Shin Ishii
Real-world decision-making problems are often partially observable, and many can be formulated as a Partially Observable Markov Decision Process (POMDP). When we apply reinforcemen…
Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learning
Sotetsu Koyamada, Shinri Okano, Soichiro Nishimori +4
We propose Pgx, a suite of board game reinforcement learning (RL) environments written in JAX and optimized for GPU/TPU accelerators. By leveraging JAX's auto-vectorization and par…
Suphx: Mastering Mahjong with Deep Reinforcement Learning
Junjie Li, Sotetsu Koyamada, Qiwei Ye +7
Artificial Intelligence (AI) has achieved great success in many domains, and game AI is widely regarded as its beachhead since the dawn of AI. In recent years, studies on game AI h…
Neural Sequence Model Training via -divergence Minimization
Sotetsu Koyamada, Yuta Kikuchi, Atsunori Kanemura +2
We propose a new neural sequence model training method in which the objective function is defined by -divergence. We demonstrate that the objective function generalizes the maxi…
Deep learning of fMRI big data: a novel approach to subject-transfer decoding
Sotetsu Koyamada, Yumi Shikauchi, Ken Nakae +2
As a technology to read brain states from measurable brain activities, brain decoding are widely applied in industries and medical sciences. In spite of high demands in these appli…
Principal Sensitivity Analysis
Sotetsu Koyamada, Masanori Koyama, Ken Nakae +1
We present a novel algorithm (Principal Sensitivity Analysis; PSA) to analyze the knowledge of the classifier obtained from supervised machine learning techniques. In particular, w…