Tatsuya Matsushima
4 papers · 2021–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🌍
Conference Polyglot
(4)
🐝
Cross-Pollinator
(13)
👑
Triple Crown
Conferences
ICLR (1)
ICML (1)
IJCAI (1)
NIPS (1)
Top co-authors
Research topics
Keywords
deep reinforcement learning
(2)
reinforcement learning
(1)
human-robot interaction
(1)
mutual information
(1)
robot control
(1)
foundation model
(1)
reward shaping
(1)
information-theoretic measure
(1)
task difficulty
(1)
task complexity
(1)
policy information capacity
(1)
information-theoretic metric
(1)
episodic return
(1)
algorithm ablation
(1)
physical risk control
(1)
Papers
A Comprehensive Survey on Physical Risk Control in the Era of Foundation Model-enabled Robotics
IJCAI 2025
Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning
NIPS 2021
Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization
ICLR 2021
Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning
ICML 2021