Common Language for Goal-Oriented Semantic Communications: A Curriculum Learning Framework
This work addresses the challenge of goal-oriented semantic communications for next-generation wireless systems, which is incremental as it builds on prior art by extending it to task execution.
The paper tackles the problem of enabling goal-oriented semantic communications by proposing a framework that defines a common language using beliefs to describe environment observations, optimizing for minimal beliefs, task execution time, and transmission cost. Simulation results show that the proposed curriculum learning method outperforms traditional reinforcement learning in convergence time, task execution time, and transmission cost during training.
Semantic communications will play a critical role in enabling goal-oriented services over next-generation wireless systems. However, most prior art in this domain is restricted to specific applications (e.g., text or image), and it does not enable goal-oriented communications in which the effectiveness of the transmitted information must be considered along with the semantics so as to execute a certain task. In this paper, a comprehensive semantic communications framework is proposed for enabling goal-oriented task execution. To capture the semantics between a speaker and a listener, a common language is defined using the concept of beliefs to enable the speaker to describe the environment observations to the listener. Then, an optimization problem is posed to choose the minimum set of beliefs that perfectly describes the observation while minimizing the task execution time and transmission cost. A novel top-down framework that combines curriculum learning (CL) and reinforcement learning (RL) is proposed to solve this problem. Simulation results show that the proposed CL method outperforms traditional RL in terms of convergence time, task execution time, and transmission cost during training.