activity
20172020
most citedReinforcement Learning for Non-Stationary Markov Decision Processes: The Blessing of (More) Optimism

25 citations · 33 across the 8 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2020

Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective

Dylan J. Foster, Alexander Rakhlin, David Simchi-Levi +1

In the classical multi-armed bandit problem, instance-dependent algorithms attain improved performance on "easy" problems with a gap between the best and second-best arm. Are simil…

cs.LG2020

Provably More Efficient Q-Learning in the One-Sided-Feedback/Full-Feedback Settings

Xiao-Yue Gong, David Simchi-Levi

Motivated by the episodic version of the classical inventory control problem, we propose a new Q-learning-based algorithm, Elimination-Based Half-Q-Learning (HQL), that enjoys impr…

cs.LG202025 cited

Reinforcement Learning for Non-Stationary Markov Decision Processes: The Blessing of (More) Optimism

Wang Chi Cheung, David Simchi-Levi, Ruihao Zhu

We consider un-discounted reinforcement learning (RL) in Markov decision processes (MDPs) under drifting non-stationarity, i.e., both the reward and state transition distributions…

cs.LG2019

Non-Stationary Reinforcement Learning: The Blessing of (More) Optimism

Wang Chi Cheung, David Simchi-Levi, Ruihao Zhu

We consider un-discounted reinforcement learning (RL) in Markov decision processes (MDPs) under temporal drifts, ie, both the reward and state transition distributions are allowed…

cs.LG2019

Phase Transitions in Bandits with Switching Constraints

David Simchi-Levi, Yunzong Xu

We consider the classical stochastic multi-armed bandit problem with a constraint that limits the total cost incurred by switching between actions to be no larger than a given swit…

cs.LG2019

Hedging the Drift: Learning to Optimize under Non-Stationarity

Wang Chi Cheung, David Simchi-Levi, Ruihao Zhu

We introduce data-driven decision-making algorithms that achieve state-of-the-art \emph{dynamic regret} bounds for non-stationary bandit settings. These settings capture applicatio…