32 citations · 55 across the 10 of their papers we have counts for
10 papers
Model-based Offline Reinforcement Learning with Local Misspecification
Kefan Dong, Yannis Flet-Berliac, Allen Nie +1
We present a model-based offline reinforcement learning policy performance lower bound that explicitly captures dynamics model misspecification and distribution mismatch and we pro…
First Steps Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains
Kefan Dong, Tengyu Ma
Real-world machine learning applications often involve deploying neural networks to domains that are not seen in the training time. Hence, we need to understand the extrapolation o…
Asymptotic Instance-Optimal Algorithms for Interactive Decision Making
Kefan Dong, Tengyu Ma
Past research on interactive decision making problems (bandits, reinforcement learning, etc.) mostly focuses on the minimax regret that measures the algorithm's performance on the…
Design of Experiments for Stochastic Contextual Linear Bandits
Andrea Zanette, Kefan Dong, Jonathan Lee +1
In the stochastic linear contextual bandit setting there exist several minimax procedures for exploration with policies that are reactive to the data being acquired. In practice, t…
Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature
Kefan Dong, Jiaqi Yang, Tengyu Ma
This paper studies model-based bandit and reinforcement learning (RL) with nonlinear function approximations. We propose to study convergence to approximate local maxima because we…
Refined Analysis of FPL for Adversarial Markov Decision Processes
Yuanhao Wang, Kefan Dong
We consider the adversarial Markov Decision Process (MDP) problem, where the rewards for the MDP can be adversarially chosen, and the transition function can be either known or unk…
Multinomial Logit Bandit with Low Switching Cost
Kefan Dong, Yingkai Li, Qin Zhang +1
We study multinomial logit bandit with limited adaptivity, where the algorithms change their exploration actions as infrequently as possible when achieving almost optimal minimax r…
-Regret for Learning in Markov Decision Processes with Function Approximation and Low Bellman Rank
Kefan Dong, Jian Peng, Yining Wang +1
In this paper, we consider the problem of online learning of Markov decision processes (MDPs) with very large state spaces. Under the assumptions of realizable function approximati…
Exploration via Hindsight Goal Generation
Zhizhou Ren, Kefan Dong, Yuan Zhou +2
Goal-oriented reinforcement learning has recently been a practical framework for robotic manipulation tasks, in which an agent is required to reach a certain goal defined by a func…
Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP
Kefan Dong, Yuanhao Wang, Xiaoyu Chen +1
A fundamental question in reinforcement learning is whether model-free algorithms are sample efficient. Recently, Jin et al. \cite{jin2018q} proposed a Q-learning algorithm with UC…