A New Framework For Multi-agent Reinforcement Learning -- Centralized Training And Exploration With Decentralized Execution Via Policy Distillation

Abstract

Deep reinforcement learning (DRL) is a booming area of artificial intelligence. Many practical applications of DRL naturally involve more than one collaborative learners, making it important to study DRL in a multi-agent context. Previous research showed that effective learning in complex multi-agent systems demands for highly coordinated environment exploration among all the participating agents. Many researchers attempted to cope with this challenge through learning centralized value functions. However, the common strategy for every agent to learn their local policies directly often fail to nurture strong inter-agent collaboration and can be sample inefficient whenever agents alter their communication channels. To address these issues, we propose a new framework known as centralized training and exploration with decentralized execution via policy distillation. Guided by this framework and the maximum-entropy learning technique, we will first train agents' policies with shared global

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keychen2019a

Related papers

• Scalable Centralized Deep Multi-agent Reinforcement Learning Via Policy Gradients (2018)0.00
• Centralized Model And Exploration Policy For Multi-agent RL (2021)0.00
• Centralized Cooperative Exploration Policy For Continuous Control Tasks (2023)0.00
• Deep Multiagent Reinforcement Learning: Challenges And Directions (2021)0.00
• Fully Decentralized Cooperative Multi-agent Reinforcement Learning: A Survey (2024)0.00
• Decentralized Multi-agents By Imitation Of A Centralized Controller (2019)0.00
• Policy Distillation And Value Matching In Multiagent Reinforcement Learning (2019)10.48
• Deep Multi-agent Reinforcement Learning With Discrete-continuous Hybrid Action Spaces (2019)12.47