Junyan Liu
5 papers · 2023–2025 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Conference Polyglot
(2)
π
Interdisciplinary Bridge
π§
Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
NIPS (3)
ICML (2)
Top co-authors
Keywords
regret bound
(3)
online reinforcement learning
(2)
online learning
(1)
regret minimization
(1)
pac bound
(1)
multi-armed bandit
(1)
bandit problem
(1)
optimistic algorithm
(1)
tsallis entropy
(1)
adversarial mdp
(1)
black-box reduction
(1)
adversarial transition
(1)
stochastic optimization
(1)
uniform last-iterate guarantee
(1)
offline reinforcement learning
(1)
Papers
Learning to Incentivize in Repeated Principal-Agent Problems with Adversarial Agent Arrivals
ICML 2025
Principal-Agent Bandit Games with Self-Interested and Exploratory Learning Agents
ICML 2025
Uniform Last-Iterate Guarantee for Bandits and Reinforcement Learning
NIPS 2024
Improved Best-of-Both-Worlds Guarantees for Multi-Armed Bandits: FTRL with General Regularizers and Multiple Optimal Arms
NIPS 2023
No-Regret Online Reinforcement Learning with Adversarial Losses and Transitions
NIPS 2023