Continual Model-based Reinforcement Learning for Data Efficient Wireless Network Optimisation
This work addresses deployment efficiency for wireless network operators, but it is incremental as it builds on existing continual learning methods applied to a specific domain.
The paper tackles the problem of long deployment lead-times for cell-level parameter optimization policies in new wireless network sites by formulating throughput optimization as continual reinforcement learning, achieving a two-fold reduction in end-to-end deployment lead-time without loss in optimization gain compared to a baseline.
We present a method that addresses the pain point of long lead-time required to deploy cell-level parameter optimisation policies to new wireless network sites. Given a sequence of action spaces represented by overlapping subsets of cell-level configuration parameters provided by domain experts, we formulate throughput optimisation as Continual Reinforcement Learning of control policies. Simulation results suggest that the proposed system is able to shorten the end-to-end deployment lead-time by two-fold compared to a reinitialise-and-retrain baseline without any drop in optimisation gain.