Plasticity-Enhanced Multi-Agent Mixture of Experts for Dynamic Objective Adaptation in UAVs-Assisted Emergency Communication Networks
On the map: Mixture-of-experts → MoE in reinforcement learning and robotics
Abstract (arXiv)
Unmanned aerial vehicles serving as aerial base stations can rapidly restore connectivity after disasters, yet abrupt changes in user mobility and traffic demands shift the quality of service trade-offs and induce strong non-stationarity. Deep reinforcement learning policies suffer from plasticity loss under such shifts, as representation collapse and neuron dormancy impair adaptation. We propose plasticity enhanced multi-agent mixture of experts (PE-MAMoE), a centralized training with decentralized execution framework built on multi-agent proximal policy optimization. PE-MAMoE equips each UAV with a sparsely gated mixture of experts actor whose router selects a single specialist per step. A non-parametric Phase Controller injects brief, expert-only stochastic perturbations after phase switches, resets the action log-standard-deviation, anneals entropy and learning rate, and schedules the router temperature, all to re-plasticize the policy without destabilizing safe behaviors. We derive a dynamic regret bound showing the tracking error scales with both environment variation and cumulative noise energy. In a phase-driven simulator with mobile users and 3GPP-style channels, PE-MAMoE improves normalized interquartile mean return by 26.3% over the best baseline, increases served-user capacity by 12.8%, and reduces collisions by approximately 75%. Diagnostics confirm persistently higher expert feature rank and periodic dormant-neuron recovery at regime switches.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in MoE in reinforcement learning and robotics, one of 12 directions in Mixture-of-experts. Builds on 36 of its 63 references that are in the map. First posted on arXiv 10 Apr 2026.
Builds on
36 of 63 references.
Closest ancestors · 1
Same direction, newest first
Other references · 35
- 2017Proximal Policy Optimization Algorithmscited by 14,441
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
- 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
- 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,014
- 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
- 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 781
- 2017Counterfactual Multi-Agent Policy Gradientscited by 733
- 2022Mixture-of-Experts with Expert Choice Routingcited by 611
- 2022The Primacy Bias in Deep Reinforcement Learningcited by 242
- 2017Learning with Opponent-Learning Awarenesscited by 218
- 2023The Dormant Neuron Phenomenon in Deep Reinforcement Learningcited by 171
23 more
- 2023Understanding plasticity in neural networkscited by 170
- 2020ROMA: Multi-Agent Reinforcement Learning with Emergent Rolescited by 135
- 2023Loss of Plasticity in Continual Deep Reinforcement Learningcited by 118
- 2017Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learningcited by 114
- 2019Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learningcited by 90
- 2021Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharingcited by 85
- 2024Disentangling the Causes of Plasticity Loss in Neural Networkscited by 82
- 2020Reinforcement Learning for Non-Stationary Markov Decision Processes: The Blessing of (More) Optimismcited by 75
- 2024An Introduction to Centralized Training for Decentralized Execution in Cooperative Multi-Agent Reinforcement Learningcited by 46
- 2023Maintaining Plasticity in Deep Continual Learningcited by 42
- 2024Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networkscited by 40
- 2019Trust Region-Guided Proximal Policy Optimizationcited by 36
- 2020Dynamic Regret of Policy Optimization in Non-stationary Environmentscited by 32
- 2017Joint Trajectory and Communication Design for Multi-UAV Enabled Wireless Networkscited by 31
- 2022Proximal Learning With Opponent-Learning Awarenesscited by 20
- 2024Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Resetcited by 17
- 2025DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Modelscited by 17
- 2023Multi-agent Continual Coordination via Progressive Task Contextualizationcited by 10
- 2022A Theoretical View on Sparsely Activated Networkscited by 6
- 2025A Survey on DRL based UAV Communications and Networking: DRL Fundamentals, Applications and Implementationscited by 4
- 2025PPO in the Fisher-Rao geometrycited by 4
- 2024Quantum Computing in Wireless Communications and Networking: A Tutorial-cum-Surveycited by 3
- 2022Enabling Personalized Video Quality Optimization with VidHoccited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025Scalable UAV Multi-Hop Networking via Multi-Agent Reinforcement Learning with Large Language Models
- 2026Spatiotemporal Continual Federated Learning for Agentic Multi-UAV Edge Networks: Mitigating Catastrophic Forgetting
- 2026Zero-Shot Scalable Resilience in UAV Swarms: A Decentralized Imitation Learning Framework with Physics-Informed Graph Interactions
- 2026Agentic AI Networking for Heterogeneous Unmanned Aerial Systems in Low-Altitude Wireless Networks
- 2026Deep Reinforcement Learning: From First Principles to Reasoning Models ↗
- 2025Agentic AI Empowered Multi-UAV Trajectory Optimization in Low-Altitude Economy Networks ↗
- 2025MAGNNET: Multi-Agent Graph Neural Network-based Efficient Task Allocation for Autonomous Vehicles with Deep Reinforcement Learning
- 2024DNN Task Assignment in UAV Networks: A Generative AI Enhanced Multi-Agent Reinforcement Learning Approach