Deep Multiagent Reinforcement Learning: Challenges And Directions

Abstract

This paper surveys the field of deep multiagent reinforcement learning. The combination of deep neural networks with reinforcement learning has gained increased traction in recent years and is slowly shifting the focus from single-agent to multiagent environments. Dealing with multiple agents is inherently more complex as (a) the future rewards depend on multiple players' joint actions and (b) the computational complexity increases. We present the most common multiagent problem representations and their main challenges, and identify five research areas that address one or more of these challenges: centralised training and decentralised execution, opponent modelling, communication, efficient coordination, and reward shaping. We find that many computational studies rely on unrealistic assumptions or are not generalisable to other settings; they struggle to overcome the curse of dimensionality or nonstationarity. Approaches from psychology and sociology capture promising relevant behaviou

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywong2021deep

Related papers

• Deep Reinforcement Learning For Multi-agent Systems: A Review Of Challenges, Solutions And Applications (2018)22.57
• Multi-agent Reinforcement Learning: A Report On Challenges And Approaches (2018)0.00
• Deep Reinforcement Learning For Multi-agent Interaction (2022)9.23
• A Review Of Cooperative Multi-agent Deep Reinforcement Learning (2019)19.08
• A Survey And Critique Of Multiagent Deep Reinforcement Learning (2018)20.07
• Fully Decentralized Cooperative Multi-agent Reinforcement Learning: A Survey (2024)0.00
• Multi-agent Reinforcement Learning: A Comprehensive Survey (2023)0.00
• Decentralized Multi-agent Reinforcement Learning With Networked Agents: Recent Advances (2019)0.00