Tanmay Sen

FedMHAR: Federated Multimodal Human Activity Recognition using Multi-Agent Reinforcement Learning

An adaptive and cost-aware multimodal HAR framework based on multi-agent reinforcement learning for centralized HAR and extended to federated learning as FedMHAR is proposed and BiFL-PPO, a bidirectional federated optimization strategy in which a server-side PPO policy learns client-specific trust weights and feeds the...