Multi-Objective Optimization Using Adaptive Distributed Reinforcement Learning

arXiv:2403.08879v1 Announce Type: new
Abstract: The Intelligent Transportation System (ITS) environment is known to be dynamic and distributed, where participants (vehicle users, operators, etc.) have multiple, changing and possibly conflicting objectives. Although Reinforcement Learning (RL) algorithms are commonly applied to optimize ITS applications such as resource management and offloading, most RL algorithms focus on single objectives. In many situations, converting a multi-objective problem into a single-objective one is impossible, intractable or insufficient, making such RL algorithms inapplicable. We propose a …

abstract algorithms applications arxiv cs.ai cs.lg cs.ma distributed dynamic environment etc focus intelligent intelligent transportation management multi-objective multiple operators optimization reinforcement reinforcement learning resource management transportation type