Chengzhuo Ni
7 papers · 2021–2023 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
๐ Conference Polyglot (4) ๐ Renaissance Researcher (5) ๐ Interdisciplinary Bridge ๐บ๏ธ Taxonomy Completionist (19) ๐งญ Keyword Pioneer
๐ฃ
Hot Topic Early Bird
๐
Cross-Pollinator
(15)
Conferences
NIPS (3)
ICML (2)
ICLR (1)
JMLR (1)
Top co-authors
Keywords
variance reduction
(2)
policy gradient
(2)
asymptotic normality
(2)
reinforcement learning
(1)
policy evaluation
(1)
off-policy evaluation
(1)
state abstraction
(1)
statistical inference
(1)
global convergence
(1)
sample complexity
(1)
tensor decomposition
(1)
markov decision process
(1)
importance sampling
(1)
state representation
(1)
value function approximation
(1)
reward function
(1)
sequence optimization
(1)
off-policy learning
(1)
bayesian optimization
(1)
thompson sampling
(1)
Papers
Representation Learning for Low-rank General-sum Markov Games
ICLR 2023
Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvement
NIPS 2023
Learning Good State and Action Representations for Markov Decision Process via Tensor Decomposition
JMLR 2023
Optimal Estimation of Policy Gradient via Double Fitted Iteration
ICML 2022
Bandit Theory and Thompson Sampling-Guided Directed Evolution for Sequence Optimization
NIPS 2022
Off-Policy Fitted Q-Evaluation with Differentiable Function Approximators: Z-Estimation and Inference Theory
ICML 2022
On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method
NIPS 2021