65 citations · 367 across the 30 of their papers we have counts for
7 papers · 1 filter
Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation
Yihong Guo, Yixuan Wang, Yuanyuan Shi +2
Training a policy in a source domain for deployment in the target domain under a dynamics shift can be challenging, often resulting in performance degradation. Previous work tackle…
Robust Offline Reinforcement Learning with Linearly Structured f-Divergence Regularization
Cheng Tang, Zhishuai Liu, Pan Xu
The Robust Regularized Markov Decision Process (RRMDP) is proposed to learn policies robust to dynamics shifts by adding regularization to the transition dynamics in the value func…
More Efficient Randomized Exploration for Reinforcement Learning via Approximate Sampling
Haque Ishfaq, Yixin Tan, Yu Yang +5
Thompson sampling (TS) is one of the most popular exploration techniques in reinforcement learning (RL). However, most TS algorithms with theoretical guarantees are difficult to im…
Optimal Batched Linear Bandits
Xuanfei Ren, Tianyuan Jin, Pan Xu
We introduce the E algorithm for the batched linear bandit problem, incorporating an Explore-Estimate-Eliminate-Exploit framework. With a proper choice of exploration rate, we…
Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning
Hao-Lun Hsu, Weixin Wang, Miroslav Pajic +1
We present the first study on provably efficient randomized exploration in cooperative multi-agent reinforcement learning (MARL). We propose a unified algorithm framework for rando…
Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning
Zhishuai Liu, Pan Xu
Distributionally robust offline reinforcement learning (RL), which seeks robust policy training against environment perturbation by modeling dynamics uncertainty, calls for functio…
Distributionally Robust Off-Dynamics Reinforcement Learning: Provable Efficiency with Linear Function Approximation
Zhishuai Liu, Pan Xu
We study off-dynamics Reinforcement Learning (RL), where the policy is trained on a source domain and deployed to a distinct target domain. We aim to solve this problem via online…