Viraj Mehta
9 papers · 2018–2024 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Conference Polyglot (5) π Academic Marathon (6) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (15) π§ Keyword Pioneer
π£
Hot Topic Early Bird
π
Cross-Pollinator
(15)
Conferences
ICLR (3)
ICML (2)
NIPS (2)
L4DC (1)
RSS (1)
Top co-authors
Keywords
model-based reinforcement learning
(2)
generative modeling
(1)
reinforcement learning
(1)
sample efficiency
(1)
offline reinforcement learning
(1)
preference optimization
(1)
procedural generation
(1)
deep learning
(1)
exploration planning
(1)
theoretical analysis
(1)
reinforcement learning from human feedback
(1)
gradient descent
(1)
generative model
(1)
information gain
(1)
normalizing flow
(1)
language model
(1)
dynamics model
(1)
feedback control
(1)
plasma control
(1)
group robustness
(1)
Papers
Position: Opportunities Exist for Machine Learning in Magnetic Fusion Energy
ICML 2024
Group Robust Preference Optimization in Reward-free RLHF
NIPS 2024
Near-optimal Policy Identification in Active Reinforcement Learning
ICLR 2023
Offline Model-Based Reinforcement Learning for Tokamak Control
L4DC 2023
Exploration via Planning for Information about the Optimal Trajectory
NIPS 2022
Variational autoencoders in the presence of low-dimensional data: landscape and implicit bias
ICLR 2022
An Experimental Design Perspective on Model-Based Reinforcement Learning
ICLR 2022
Representational aspects of depth and conditioning in normalizing flows
ICML 2021
Learning Task-Oriented Grasping for Tool Manipulation from Simulated Self-Supervision
RSS 2018