Awesome Reinforcement Learning
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
Soichiro Nishimori — most-cited papers & profile · Reinforcement Learning
← authors
·
overview
Soichiro Nishimori
8
papers ·
5
citations ·
1
h-index
RIKEN Center for Advanced Intelligence Project · The University of Tokyo
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learning
2023 · 5 citations
Mahjax: A GPU-Accelerated Mahjong Simulator for Reinforcement Learning in JAX
2026
Mitigating Reward Hacking in RLHF via Advantage Sign Robustness
2026
Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying
2026
On Advantage Estimates for Max@K Policy Gradients
2026
End-to-End Policy Gradient Method for POMDPs and Explainable Agents
2023
A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees
2024
Offline Reinforcement Learning with Domain-Unlabeled Data
2024
Top co-authors
Sotetsu Koyamada
· 4
Johannes Ackermann
· 2
Keigo Habara
· 2
Paavo Parmas
· 2
Shin Ishii
· 2
Shinri Okano
· 2
Tadashi Kozuno
· 2
Toshinori Kitamura
· 2
Akiyoshi Sannai
· 1
and Masashi Sugiyama
· 1
Eason Yu
· 1
Gouki Minegishi
· 1
Topics
Policy Gradient
Model-Based RL
Safe RL
Game AI
RLHF & Alignment
Exploration
Multi-Agent
Value-Based
Offline RL