20 citations · 43 across the 18 of their papers we have counts for
6 papers · 1 filter
Rethinking Decision Transformer via Hierarchical Reinforcement Learning
Yi Ma, Chenjun Xiao, Hebin Liang +1
Decision Transformer (DT) is an innovative algorithm leveraging recent advances of the transformer architecture in reinforcement learning (RL). However, a notable limitation of DT…
Scaff-PD: Communication Efficient Fair and Robust Federated Learning
Yaodong Yu, Sai Praneeth Karimireddy, Yi Ma +1
We present Scaff-PD, a fast and communication-efficient algorithm for distributionally robust federated learning. Our approach improves fairness by optimizing a family of distribut…
HIPODE: Enhancing Offline Reinforcement Learning with High-Quality Synthetic Data from a Policy-Decoupled Approach
Shixi Lian, Yi Ma, Jinyi Liu +2
Offline reinforcement learning (ORL) has gained attention as a means of training reinforcement learning models using pre-collected static data. To address the issue of limited data…
ENOTO: Improving Offline-to-Online Reinforcement Learning with Q-Ensembles
Kai Zhao, Jianye Hao, Yi Ma +3
Offline reinforcement learning (RL) is a learning paradigm where an agent learns from a fixed dataset of experience. However, learning solely from a static dataset can limit the pe…
Iteratively Refined Behavior Regularization for Offline Reinforcement Learning
Xiaohan Hu, Yi Ma, Chenjun Xiao +2
One of the fundamental challenges for offline reinforcement learning (RL) is ensuring robustness to data distribution. Whether the data originates from a near-optimal policy or not…
Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning
Mitsuhiko Nakamoto, Yuexiang Zhai, Anikait Singh +5
A compelling use case of offline reinforcement learning (RL) is to obtain a policy initialization from existing datasets followed by fast online fine-tuning with limited interactio…