Multi-Objective Deep Reinforcement Learning for Optimisation in Autonomous Systems

TL;DR

This paper applies a multi-objective deep reinforcement learning technique to optimize autonomous system configurations, demonstrating its effectiveness in balancing multiple goals without predefined weights.

Contribution

It introduces the use of Deep W-Learning for multi-objective optimization in real-world autonomous systems, outperforming traditional single-objective methods in some metrics.

Findings

DWN optimizes multiple objectives simultaneously.

DWN performs comparably to DQN and ε-greedy methods.

DWN avoids issues of combining objectives into a single utility.

Abstract

Reinforcement Learning (RL) is used extensively in Autonomous Systems (AS) as it enables learning at runtime without the need for a model of the environment or predefined actions. However, most applications of RL in AS, such as those based on Q-learning, can only optimize one objective, making it necessary in multi-objective systems to combine multiple objectives in a single objective function with predefined weights. A number of Multi-Objective Reinforcement Learning (MORL) techniques exist but they have mostly been applied in RL benchmarks rather than real-world AS systems. In this work, we use a MORL technique called Deep W-Learning (DWN) and apply it to the Emergent Web Servers exemplar, a self-adaptive server, to find the optimal configuration for runtime performance optimization. We compare DWN to two single-objective optimization implementations: {\epsilon}-greedy algorithm and Deep Q-Networks. Our initial evaluation shows that DWN optimizes multiple objectives simultaneously with similar results than DQN and {\epsilon}-greedy approaches, having a better performance for some metrics, and avoids issues associated with combining multiple objectives into a single utility function.