Eiji Uchibe

3 papers · 2009–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Full 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird 📈 Trend Setter

Venues

ACL (1) AISTATS (1) NeurIPS (1)

Top co-authors

Kenji Doya (2) Tetsuro Morimura (2) Kaito Ariu (1) Yuu Jinnai (1) Yuki Ichihara (1) Junichiro Yoshimoto (1) Tadashi Kozuno (1)

Research topics

Machine Learning (3) Reinforcement Learning (2) Learning Types · Machine Learning (2) Methods (2) Optimization & Theory (2) Artificial Intelligence (1) Deep Learning (1) Applications (1) Core AI (1) Learning Types · Deep Learning (1)

Keywords

reinforcement learning (2) policy gradient (1) text generation (1) policy learning (1) theoretical analysis (1) utility optimization (1) natural gradient (1) value iteration (1) variance reduction (1) fisher information matrix (1) actor-critic algorithm (1) minimum bayes risk (1) softmax operator (1) actor critic (1) gap-increasing operator (1) bayesian decoding (1) reference hypothesis (1)

Papers

Theoretical Guarantees for Minimum Bayes Risk Decoding ACL 2025 Theoretical Analysis of Efficiency and Robustness of Softmax and Gap-Increasing Operators in Reinforcement Learning AISTATS 2019 A Generalized Natural Actor-Critic Algorithm NeurIPS 2009