CALF: Communication-Aware Learning Framework for Distributed Reinforcement Learning
Distributed reinforcement learning policies face network delays, jitter, and packet loss when deployed across edge devices and cloud servers. Standard RL training assumes zero-latency interaction, causing severe performance degradation under realistic network conditions. We introduce CALF (Communication-Aware Learning Framework), which trains policies under realistic network models during simulation. Systematic experiments demonstrate that network-aware training substantially reduces deployment performance gaps compared to network-agnostic baselines. Distributed policy deployments across heterogeneous hardware validate that explicitly modelling communication constraints during training enables robust real-world execution. These findings establish network conditions as a major axis of sim-to-real transfer for Wi-Fi-like distributed deployments, complementing physics and visual domain randomisation.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningSimilar Papers 제목 키워드 기반
QoS and Jamming-Aware Wireless Networking Using Deep Reinforcement Learning
The problem of quality of service (QoS) and jamming-aware communications is considered in an adversarial wireless network subject to external eavesdropping and jamming attacks. To ensure robust communication against jamm…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Critic as Lyapunov function (CALF): a model-free, stability-ensuring agent
This work presents and showcases a novel reinforcement learning agent called Critic As Lyapunov Function (CALF) which is model-free and ensures online environment, in other words, dynamical system stabilization. Online m…
Model Predictive Controlreinforcement-learningReinforcement LearningNetwork Distributed Multi-Agent Reinforcement Learning for Consensus Control of Quadcopters
This paper proposes a Network Distributed Multi-Agent Reinforcement Learning (ND-MARL) framework for quadcopter consensus control. Compared to conventional multi-agent MARL formulations that rely on centralized planning …
Multi-agent Reinforcement LearningToward Multi-Agent Reinforcement Learning for Distributed Event-Triggered Control
Event-triggered communication and control provide high control performance in networked control systems without overloading the communication network. However, most approaches require precise mathematical models of the s…
Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningA novel agent with formal goal-reaching guarantees: an experimental study with a mobile robot
Reinforcement Learning (RL) has been shown to be effective and convenient for a number of tasks in robotics. However, it requires the exploration of a sufficiently large number of state-action pairs, many of which may be…
Reinforcement Learning (RL)