Chengshuai Shi
15 papers · 2020–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
π Academic Marathon (5) π§ Keyword Pioneer π Interdisciplinary Bridge π Conference Polyglot (7) π Cross-Pollinator (12)
π
Renaissance Researcher
(6)
πΊοΈ
Taxonomy Completionist
(30)
π
Conference Polyglot
(7)
π
Grand Slam
π€
Dynamic Duo
(14)
π
Century Club
(15)
π₯
Unstoppable
(6)
Conferences
NIPS (5)
AISTATS (3)
ICLR (2)
ICML (2)
AAAI (1)
EMNLP (1)
UAI (1)
Top co-authors
Keywords
multi-armed bandit
(5)
in-context learning
(4)
regret bound
(4)
upper confidence bound
(3)
best arm identification
(2)
markov game
(2)
decentralized learning
(2)
federated learning
(2)
multi-player multi-armed bandit
(2)
zero-sum game
(2)
stochastic process
(1)
nash equilibrium
(1)
label propagation
(1)
multi-agent reinforcement learning
(1)
theoretical analysis
(1)
robust reinforcement learning
(1)
offline reinforcement learning
(1)
data heterogeneity
(1)
language model
(1)
posterior sampling
(1)
Papers
Building Math Agents with Multi-Turn Iterative Preference Learning
ICLR 2025
Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis
UAI 2025
From Cross-Task Examples to In-Task Prompts: A Graph-Based Pseudo-Labeling Framework for In-context Learning
EMNLP 2025
Cost-Aware Optimal Pairwise Pure Exploration
AISTATS 2025
Mixture of Demonstrations for In-Context Learning
NIPS 2024
Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Models
NIPS 2024
Efficient Prompt Optimization Through the Lens of Best Arm Identification
NIPS 2024
Provably Efficient Offline Reinforcement Learning with Perturbed Data Sources
ICML 2023
Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game
ICLR 2023
A Self-Play Posterior Sampling Algorithm for Zero-Sum Markov Games
ICML 2022
Federated Multi-armed Bandits with Personalization
AISTATS 2021
Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization
NIPS 2021
Federated Multi-Armed Bandits
AAAI 2021
(Almost) Free Incentivized Exploration from Decentralized Learning Agents
NIPS 2021
Decentralized Multi-player Multi-armed Bandits with No Collision Information
AISTATS 2020