Log In Sign Up

Coding for Distributed Multi-Agent Reinforcement Learning

by   Baoqian Wang, et al.

This paper aims to mitigate straggler effects in synchronous distributed learning for multi-agent reinforcement learning (MARL) problems. Stragglers arise frequently in a distributed learning system, due to the existence of various system disturbances such as slow-downs or failures of compute nodes and communication bottlenecks. To resolve this issue, we propose a coded distributed learning framework, which speeds up the training of MARL algorithms in the presence of stragglers, while maintaining the same accuracy as the centralized approach. As an illustration, a coded distributed version of the multi-agent deep deterministic policy gradient(MADDPG) algorithm is developed and evaluated. Different coding schemes, including maximum distance separable (MDS)code, random sparse code, replication-based code, and regular low density parity check (LDPC) code are also investigated. Simulations in several multi-robot problems demonstrate the promising performance of the proposed framework.


Multi-Agent Reinforcement Learning for Cooperative Coded Caching via Homotopy Optimization

Introducing cooperative coded caching into small cell networks is a prom...

Coded FFT and Its Communication Overhead

We propose a coded computing strategy and examine communication costs of...

Efficient Distributed Framework for Collaborative Multi-Agent Reinforcement Learning

Multi-agent reinforcement learning for incomplete information environmen...

The Emergence of Complex Bodyguard Behavior Through Multi-Agent Reinforcement Learning

In this paper we are considering a scenario where a team of robot bodygu...

Communication-Efficient Distributed Reinforcement Learning

This paper studies the distributed reinforcement learning (DRL) problem ...

Safety-Aware Multi-Agent Apprenticeship Learning

Our objective of this project is to make the extension based on the tech...

TLeague: A Framework for Competitive Self-Play based Distributed Multi-Agent Reinforcement Learning

Competitive Self-Play (CSP) based Multi-Agent Reinforcement Learning (MA...