cs.RONov 19, 2026

Beyond Easy Clients: Difficulty- and Improvement-Aware Aggregation for Federated Reinforcement Learning in Robot Navigation

Authors: Ye Lin Tun, Chu Myaet Thwal, Eui-Nam Huh, Choong Seon Hong

Organizations: Kyung Hee University, Republic of Korea

Abstract

Federated reinforcement learning enables a fleet of robots to jointly learn a shared navigation policy without exchanging raw experience. In practice, however, the robots rarely operate in the same conditions: an open aisle is far easier to navigate than a cluttered room, and takes less learning to master. Standard federated aggregation rules ignore this. Uniform averaging weights every client equally, whether or not it is still learning, and weighting by episode return is worse, since easy environments permit high returns by construction. Both failures stem from what we call the plateau problem: once a client masters its environment, its updates carry little new information even though its reported return remains high. We propose FedDIA, which scores each client by how much its local training improves the global model it received, amplified by the difficulty of its environment. Difficulty is inferred from the model's own performance, without requiring any description of the environment. Both signals are measured against the global model, so they are comparable across clients. On a mapless navigation task with eight heterogeneous clients, FedDIA reaches a mean success rate of 75.5%75.5\% across training and held-out environments, against 68.7%68.7\% for the strongest federated baseline. Its advantage holds when the models are transferred to hand-authored warehouse and living-space layouts, or when one of the clients is defective.

Figures & tables

Explore similar work

CardsList
  1. Federated Subspace Guided Vision-Language-Action Policy Distillation for Non-IID Multi-Robot Manipulation

    Sep 26, 2026Biprodip Pal, Kaushik Roy, Yanming Zhu +3Federated Knowledge DistillationNon-IID Federated Learning

  2. Constraint-Aware Aggregation for Federated Reinforcement Learning in Microgrid Energy Coordination

    Jul 14, 2026Usman Haider, Karl MasonFederated Learning AggregationFederated RL

  3. Robust Federated Q-Learning with Almost No Communication

    Aug 24, 2026Sreejeet Maity, Aritra MitraFederated RLQ-Learning