Hanlin Zhu
11 papers · 2019–2025 · 6 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 ↓+3 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (27)
π
Century Club Β· Bronze
π
Renaissance Researcher
(5)
ποΈ
Keyword Collector
(63)
Top co-authors
Research topics
Machine Learning
(8)
Reinforcement Learning
(7)
Methods
(7)
Artificial Intelligence
(6)
Core AI
(6)
Optimization & Theory
(5)
Core Methods
(3)
Learning Types
(3)
Mathematics & Optimization
(2)
Natural Language Processing
(2)
Optimization
(2)
Computer Science
(1)
Deep Learning
(1)
Foundations
(1)
Generation
(1)
Keywords
offline reinforcement learning
(3)
function approximation
(2)
sample complexity
(2)
logical reasoning
(1)
inverse reinforcement learning
(1)
knowledge transfer
(1)
communication complexity
(1)
value function approximation
(1)
bellman error
(1)
policy learning
(1)
model-based reinforcement learning
(1)
empirical risk minimization
(1)
sparse principal component analysis
(1)
importance sampling
(1)
gradient descent
(1)
in-context learning
(1)
policy optimization
(1)
query complexity
(1)
reinforcement learning
(1)
augmented lagrangian
(1)
Papers
Avoiding Catastrophe in Online Learning by Asking for Help
ICML 2025
Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning
ICML 2025
Learning Personalized Alignment for Evaluating Open-ended Text Generation
EMNLP 2024
On Representation Complexity of Model-based and Model-free Reinforcement Learning
ICLR 2024
Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics
NeurIPS 2024
Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning
NeurIPS 2023
Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian
ICLR 2023
Provably Efficient Offline Goal-Conditioned Reinforcement Learning with General Function Approximation and Single-Policy Concentrability
NeurIPS 2023
Provably Efficient Reinforcement Learning via Surprise Bound
AISTATS 2023
Average-Case Communication Complexity of Statistical Problems
COLT 2021
Guided Dialog Policy Learning: Reward Estimation for Multi-Domain Task-Oriented Dialog
EMNLP 2019