Qingyuan Wu
6 papers · 2024–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
๐
Interdisciplinary Bridge
๐งญ
Keyword Pioneer
๐
Conference Polyglot
(3)
๐
Cross-Pollinator
(13)
Conferences
ICML (4)
L4DC (1)
NIPS (1)
Top co-authors
Keywords
reinforcement learning
(1)
sample efficiency
(1)
policy optimization
(1)
variational inference
(1)
behavior cloning
(1)
temporal-difference learning
(1)
safe reinforcement learning
(1)
safety constraint
(1)
pixel observation
(1)
delayed reinforcement learning
(1)
barrier function
(1)
safe exploration
(1)
latent dynamics model
(1)
delayed environment
(1)
Papers
Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning
ICML 2025
Directly Forecasting Belief for Reinforcement Learning with Delays
ICML 2025
Variational Delayed Policy Optimization
NIPS 2024
Highway Value Iteration Networks
ICML 2024
Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays
ICML 2024
State-wise safe reinforcement learning with pixel observations
L4DC 2024