# CALF: Communication-Aware Learning Framework for Distributed Reinforcement Learning

arXiv: https://arxiv.org/abs/2603.12543 · HTML: https://mlsanity.com/paper/2603.12543/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 18 of its 32 references that are in the map.
- First posted on arXiv 13 Mar 2026.

## Placed in

- Deep reinforcement learning methods / [RL for energy, networks and operations](https://mlsanity.com/deeprl/rl-for-energy-networks-and-operations/)

## Builds on (most cited first, 18 of 18)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [DeepMind Control Suite](https://mlsanity.com/paper/1801.00690/) (2018)
- [IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures](https://mlsanity.com/paper/1802.01561/) (2018)
- [Solving Rubik's Cube with a Robot Hand](https://mlsanity.com/paper/1910.07113/) (2019)
- [Sim-to-Real Transfer of Robotic Control with Dynamics Randomization](https://mlsanity.com/paper/1710.06537/) (2017)
- [Learning agile and dynamic motor skills for legged robots](https://mlsanity.com/paper/1901.08652/) (2019)
- [Data-Efficient Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1805.08296/) (2018)
- [The Option-Critic Architecture](https://mlsanity.com/paper/1609.05140/) (2016)
- [Learning Multiagent Communication with Backpropagation](https://mlsanity.com/paper/1605.07736/) (2016)
- [FeUdal Networks for Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1703.01161/) (2017)
- [Sim-to-Real: Learning Agile Locomotion For Quadruped Robots](https://mlsanity.com/paper/1804.10332/) (2018)
- [Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience](https://mlsanity.com/paper/1810.05687/) (2018)
- [Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning](https://mlsanity.com/paper/2006.11751/) (2020)
- [Learning Nearly Decomposable Value Functions Via Communication Minimization](https://mlsanity.com/paper/1910.05366/) (2019)
- [Reinforcement Learning with Random Delays](https://mlsanity.com/paper/2010.02966/) (2020)
- [Extending the OpenAI Gym for robotics: a toolkit for reinforcement learning using ROS and Gazebo](https://mlsanity.com/paper/1608.05742/) (2016)

## Built on by (most cited first, 1 of 1)

- [Network-in-the-Loop at Scale: GPU-Batched 5G Simulation for Massively Parallel Robot Learning](https://mlsanity.com/paper/2610.02370/) (2026)

## Abstract (arXiv)

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.