Federated offline reinforcement learning: Collaborative single-policy coverage suffices

J Woo, L Shi, G Joshi, Y Chi - arxiv preprint arxiv:2402.05876, 2024 - arxiv.org
Offline reinforcement learning (RL), which seeks to learn an optimal policy using offline data,
has garnered significant interest due to its potential in critical applications where online data …

Federated Offline Policy Optimization with Dual Regularization

S Yue, Z Qin, X Hua, Y Deng, J Ren - arxiv preprint arxiv:2405.17474, 2024 - arxiv.org
Federated Reinforcement Learning (FRL) has been deemed as a promising solution for
intelligent decision-making in the era of Artificial Internet of Things. However, existing FRL …