Akifumi Wachi

Identifiers

• name variant Akifumi Wachi 0.60 · backfill

Papers (6)

1. Interaction-Limited Safe Continuous-Time RL for Dynamical Medical Treatment cs.LG · 2026 · author #3
2. MedGym:A Unified Continuous-Time Benchmark for Dynamic Medical Treatment Reinforcement Learning cs.LG · 2026 · author #6
3. How Neural Reward Models Learn Features for Policy Optimization: A Single-Index Analysis stat.ML · 2026 · author #3
4. Sample-Efficient Hypergradient Estimation for Decentralized Bi-Level Reinforcement Learning cs.LG · 2026 · author #3
5. Failure-Scenario Maker for Rule-Based Agent using Multi-agent Adversarial Reinforcement Learning and its Application to Autonomous Driving cs.LG · 2019 · author #1
6. Safe Exploration in Markov Decision Processes with Time-Variant Safety using Spatio-Temporal Gaussian Process cs.AI · 2018 · author #1

Mentions

• 2603.14867 #3 · arxiv_oai · confidence 0.70 Akifumi Wachi
• 2606.01051 #3 · arxiv_oai · confidence 0.70 Akifumi Wachi
• 2606.01028 #6 · arxiv_oai · confidence 0.70 Akifumi Wachi
• 2605.24749 #3 · arxiv_oai · confidence 0.70 Akifumi Wachi

Frequent Coauthors

• Katsuki Fujisawa 2 shared papers
• Ken Kawano 2 shared papers
• Kyoung-Sook Kim 2 shared papers
• Mehrshad Sadria 2 shared papers
• Richard Weiss 2 shared papers
• Sebastien Gros 2 shared papers
• Xiao Hu 2 shared papers
• Xin Liu 2 shared papers
• Xun Shen 2 shared papers
• Ying Chen 2 shared papers
• Yongqi Zhou 2 shared papers
• Yoshihiko Fujisawa 2 shared papers
• Yuepeng Wang 2 shared papers
• Asim Munawar 1 shared papers
• Hiroshi Kajino 1 shared papers
• Kenji Wakabayashi 1 shared papers
• Kohei Miyaguchi 1 shared papers
• Mengmou Li 1 shared papers
• Mikoto Kudo 1 shared papers
• Rei Higuchi 1 shared papers