Abstract--This paper presents a novel and sustainable approach for improving beam selection in 5G and beyond networks using transfer learning and Reinforcement Learning (RL). Traditional RL-based beam selection models require extensive training time and computational resources, particularly when deployed in diverse environments with varying propagation characteristics posing a major challenge for scalability and energy efficiency. T o address this, we propose modeling the environment as a point cloud, where each point represents the locations of gNodeBs (gNBs) and surrounding scatterers. By computing the Chamfer distance between point clouds, structurally similar environments can be efficiently identified, enabling the reuse of pre-trained models through transfer learning. This methodology leads to a 16 reduction in training time and computational overhead, directly contributing to energy efficiency. By minimizing the need for retraining in each new deployment, our approach significantly lowers power consumption and supports the development of green and sustainable Artificial Intelligence (AI) in wireless systems. Furthermore, it accelerates time-to-deployment, reduces carbon emissions associated with training, and enhances the viability of deploying AI-driven communication systems at the edge. Simulation results confirm that our approach maintains high performance while drastically cutting energy costs, demonstrating the potential of transfer learning to enable scalable, adaptive, and environmentally conscious RL-based beam selection strategies in dynamic and diverse propagation environments.

Many reinforcement learning (RL) algorithms are too costly to use in practice due to the large sizes S,A of the problem's state and action space. To resolve this issue, we study transfer RL with latent low rank structure. We consider the problem of transferring a latent low rank representation when the source and target MDPs have transition kernels with Tucker rank (S, d, A), (S,S, d), (d, S, A), or (d, d, d) . In each setting, we introduce the transfer-ability coefficient \alpha that measures the difficulty of representational transfer. Our algorithm learns latent representations in each source MDP and then exploits the linear structure to remove the dependence on S, A, or SA in the target MDP regret bound.

Transfer learning approaches in reinforcement learning aim to assist agents in learning their target domains by leveraging the knowledge learned from other agents that have been trained on similar source domains. For example, recent research focus within this space has been placed on knowledge transfer between tasks that have different transition dynamics and reward functions; however, little focus has been placed on knowledge transfer between tasks that have different action spaces. In this paper, we approach the task of transfer learning between domains that differ in action spaces. We present a reward shaping method based on source embedding similarity that is applicable to domains with both discrete and continuous action spaces. The efficacy of our approach is evaluated on transfer to restricted action spaces in the Acrobot-v1 and Pendulum-v0 domains. A comparison with two baselines shows that our method does not outperform these baselines in these continuous action spaces but does show an improvement in these discrete action spaces. We conclude our analysis with future directions for this work.

The objective of transfer reinforcement learning is to generalize from a set of previous tasks to unseen new tasks. In this work, we focus on the transfer scenario where the dynamics among tasks are the same, but their goals differ. Although general value function (Sutton et al., 2011) has been shown to be useful for knowledge transfer, learning a universal value function can be challenging in practice. To attack this, we propose (1) to use universal successor representations (USR) to represent the transferable knowledge and (2) a USR approximator (USRA) that can be trained by interacting with the environment. Our experiments show that USR can be effectively applied to new tasks, and the agent initialized by the trained USRA can achieve the goal considerably faster than random initialization.