Takuma Seno

6 papers · 2022–2025 · 4 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 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12)

Venues

ICML (2) NeurIPS (2) ICLR (1) JMLR (1)

Top co-authors

Peter Stone (3) Paavo Parmas (2) Donghu Kim (2) Jaegul Choo (2) Hojoon Lee (2) James MacGlashan (1) Yuma Aoki (1) Peter Wurman (1) Craig Sherstan (1) Peter R. Wurman (1)

Research topics

Reinforcement Learning (5) Methods (5) Machine Learning (3) Artificial Intelligence (2) Deep Learning (2) Architectures (2) Core AI (2) Learning Types (2) Applications (1) Optimization & Theory · Machine Learning (1) Optimization & Theory · Deep Learning (1)

Keywords

deep reinforcement learning (3) soft actor-critic (2) likelihood ratio gradient (2) reparameterization gradient (2) policy gradient (1) policy learning (1) automatic differentiation (1) gradient estimation (1) message passing (1) model-based reinforcement learning (1) variance reduction (1) reward function (1) off-policy learning (1) deep rl (1) simplicity bia (1) layer normalization (1) reward decomposition (1) value decomposition (1) offline rl (1) agent design (1)

Papers

Hyperspherical Normalization for Scalable Deep Reinforcement Learning ICML 2025 SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning ICLR 2025 Model-based Reinforcement Learning with Scalable Composite Policy Gradient Estimators ICML 2023 d3rlpy: An Offline Deep Reinforcement Learning Library JMLR 2022 Proppo: a Message Passing Framework for Customizable and Composable Learning Algorithms NeurIPS 2022 Value Function Decomposition for Iterative Design of Reinforcement Learning Agents NeurIPS 2022