A Framework for History-Aware Hyperparameter Optimisation in Reinforcement Learning

TL;DR

This paper introduces a history-aware hyperparameter optimization framework for reinforcement learning that adaptively adjusts parameters during training, leading to improved stability and performance in complex systems.

Contribution

It presents a novel framework combining complex event processing and temporal models to enable runtime hyperparameter adjustments based on historical performance analysis.

Findings

Enhanced training stability and reward values with history-aware tuning

Significant performance improvements over traditional hyperparameter tuning methods

Effective resource utilization through parallel processing

Abstract

A Reinforcement Learning (RL) system depends on a set of initial conditions (hyperparameters) that affect the system's performance. However, defining a good choice of hyperparameters is a challenging problem. Hyperparameter tuning often requires manual or automated searches to find optimal values. Nonetheless, a noticeable limitation is the high cost of algorithm evaluation for complex models, making the tuning process computationally expensive and time-consuming. In this paper, we propose a framework based on integrating complex event processing and temporal models, to alleviate these trade-offs. Through this combination, it is possible to gain insights about a running RL system efficiently and unobtrusively based on data stream monitoring and to create abstract representations that allow reasoning about the historical behaviour of the RL system. The obtained knowledge is exploited to provide feedback to the RL system for optimising its hyperparameters while making effective use of parallel resources. We introduce a novel history-aware epsilon-greedy logic for hyperparameter optimisation that instead of using static hyperparameters that are kept fixed for the whole training, adjusts the hyperparameters at runtime based on the analysis of the agent's performance over time windows in a single agent's lifetime. We tested the proposed approach in a 5G mobile communications case study that uses DQN, a variant of RL, for its decision-making. Our experiments demonstrated the effects of hyperparameter tuning using history on training stability and reward values. The encouraging results show that the proposed history-aware framework significantly improved performance compared to traditional hyperparameter tuning approaches.