Omar Darwiche Domingues
9 papers · 2019–2022 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (17) π Interdisciplinary Bridge π§ Keyword Pioneer π£ Hot Topic Early Bird π Conference Polyglot (4)
π
Cross-Pollinator
(12)
π
Renaissance Researcher
(5)
β‘
Prolific Year
(6)
Conferences
ICML (3)
AISTATS (2)
ALT (2)
NIPS (2)
Top co-authors
Keywords
markov decision process
(5)
sample complexity
(5)
regret bound
(4)
non-stationary mdp
(2)
best-policy identification
(2)
reinforcement learning
(2)
reward-free exploration
(2)
kernel methods
(2)
bellman operator
(1)
kernel-based reinforcement learning
(1)
pac learning
(1)
finite-time analysis
(1)
game theory
(1)
upper confidence bound
(1)
monte-carlo tree search
(1)
metric space
(1)
linear function approximation
(1)
entropy regularization
(1)
non-parametric model
(1)
value iteration
(1)
Papers
Adaptive Multi-Goal Exploration
AISTATS 2022
A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces
AISTATS 2021
UCB Momentum Q-learning: Correcting the bias without forgetting
ICML 2021
Kernel-Based Reinforcement Learning: A Finite-Time Analysis
ICML 2021
Fast active learning for pure exploration in reinforcement learning
ICML 2021
Episodic Reinforcement Learning in Finite MDPs: Minimax Lower Bounds Revisited
ALT 2021
Adaptive Reward-Free Exploration
ALT 2021
Planning in Markov Decision Processes with Gap-Dependent Sample Complexity
NIPS 2020
Planning in entropy-regularized Markov decision processes and games
NIPS 2019