Heyang Zhao
10 papers · 2023–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (24) π Interdisciplinary Bridge Β· Silver π Conference Polyglot Β· Bronze π Triple Crown π€ Dynamic Duo (10)
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(54)
Venues
Top co-authors
Research topics
Machine Learning
(9)
Optimization & Theory
(7)
Reinforcement Learning
(6)
Learning Types Β· Machine Learning
(6)
Methods
(6)
Artificial Intelligence
(4)
Mathematics & Optimization
(4)
Optimization
(4)
Core AI
(3)
Deep Learning
(2)
Learning Types Β· Deep Learning
(2)
Bayesian & Probabilistic
(1)
Core Methods
(1)
Keywords
regret bound
(7)
function approximation
(3)
thompson sampling
(2)
contextual bandit
(2)
minimax optimal
(2)
reinforcement learning
(2)
minimax optimal regret
(2)
generalized linear model
(2)
policy optimization
(1)
value iteration
(1)
imitation learning
(1)
kl regularization
(1)
variance estimation
(1)
sample efficiency
(1)
value function
(1)
online decision making
(1)
online learning
(1)
multi-armed bandit
(1)
upper confidence bound
(1)
regret
(1)
Papers
Avoiding exp($k^*$) Scaling for Thompson Sampling in Combinatorial Semi-Bandits: From Multiple Seeds to a Single Seed
COLT 2026
Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration
ICLR 2025
Logarithmic Regret for Online KL-Regularized Reinforcement Learning
ICML 2025
A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation
NeurIPS 2024
Feel-Good Thompson Sampling for Contextual Dueling Bandits
ICML 2024
Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning
ICLR 2024
Variance-aware Regret Bounds for Stochastic Contextual Dueling Bandits
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