MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122902 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 5, 2025, for 'multi-agent reinforcement learning system for wireless device-to-device communication optimization.'
Inventor(s) include Dr S Nandakumar; Mr. Hariharan S; Mr. Anissh Babu L N; and Mr. Kaarthik S.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The present disclosure provides a multi-agent reinforcement learning system for wireless device-to-device communication optimization. The system includes autonomous agents, each corresponding to a device-to-device communication pair, wherein each agent includes a neural network policy configured to make resource allocation decisions based on network condition observations. The system further includes a centralized reward calculator configured to compute reward signals for agents based on system performance metrics, a wireless communication environment simulator configured to model signal propagation and interference between device pairs, and a Proximal Policy Optimization training module configured to update neural network policies using reward signals. The centralized reward calculator processes observations from multiple agents and generates coordinated reward signals enabling decentralized execution while maintaining system-wide optimization objectives for throughput, energy efficiency, latency, and interference management in dynamic wireless environments."
Disclaimer: Curated by HT Syndication.
