Heyang Zhao
9 papers · 2023–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (4) π Cross-Pollinator (7) πΊοΈ Taxonomy Completionist (16)
π
Triple Crown
Conferences
ICML (4)
ICLR (3)
COLT (1)
NIPS (1)
Top co-authors
Keywords
regret bound
(3)
minimax optimal regret
(2)
function approximation
(2)
reinforcement learning
(2)
eluder dimension
(1)
multi-armed bandit
(1)
upper confidence bound
(1)
online algorithm
(1)
generalized linear model
(1)
linear bandit
(1)
linear mixture mdp
(1)
heteroscedastic noise
(1)
generalized linear regression
(1)
linear markov decision process
(1)
follow the regularized leader
(1)
sub-gaussian noise
(1)
self-normalized martingale
(1)
heteroscedastic bandit
(1)
weighted linear regression
(1)
variance-dependent regret
(1)
Papers
Logarithmic Regret for Online KL-Regularized Reinforcement Learning
ICML 2025
Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration
ICLR 2025
Variance-aware Regret Bounds for Stochastic Contextual Dueling Bandits
ICLR 2024
Feel-Good Thompson Sampling for Contextual Dueling Bandits
ICML 2024
A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation
NIPS 2024
Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning
ICLR 2024
Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes
ICML 2023
Optimal Online Generalized Linear Regression with Stochastic Noise and Its Application to Heteroscedastic Bandits
ICML 2023
Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency
COLT 2023