← Back to Benchmarks
simmediumoffline-rlmetric · varies
FOVA: Offline Federated Reinforcement Learning with Mixed-Quality Data
Description
Offline Federated Reinforcement Learning (FRL), a marriage of federated learning and offline reinforcement learning, has attracted increasing interest recently. Albeit with some advancement, we find that the performance of most existing offline FRL methods drops dramatically when provided with mixed-quality data, that is, the logging behaviors (offline data) are collected by policies with varying qualities across clients. To overcome this limitation, this paper introduces a new vote-based offlin