Deep Q-network Based Multi-agent Reinforcement Learning With Binary Action Agents

Abstract

Deep Q-Network (DQN) based multi-agent systems (MAS) for reinforcement learning (RL) use various schemes where in the agents have to learn and communicate. The learning is however specific to each agent and communication may be satisfactorily designed for the agents. As more complex Deep QNetworks come to the fore, the overall complexity of the multi-agent system increases leading to issues like difficulty in training, need for higher resources and more training time, difficulty in fine-tuning, etc. To address these issues we propose a simple but efficient DQN based MAS for RL which uses shared state and rewards, but agent-specific actions, for updation of the experience replay pool of the DQNs, where each agent is a DQN. The benefits of the approach are overall simplicity, faster convergence and better performance as compared to conventional DQN based approaches. It should be noted that the method can be extended to any DQN. As such we use simple DQN and DDQN (Double Q-learning) respe

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhafiz2020deep

Related papers

• Deep Multi-agent Reinforcement Learning With Discrete-continuous Hybrid Action Spaces (2019)12.47
• Lenient Multi-agent Deep Reinforcement Learning (2017)4.52
• Towards Multi-agent Reinforcement Learning Using Quantum Boltzmann Machines (2021)0.00
• Weighted Double Deep Multiagent Reinforcement Learning In Stochastic Cooperative Environments (2018)0.00
• Modular Multi-objective Deep Reinforcement Learning With Decision Values (2017)10.74
• Simplified Action Decoder For Deep Multi-agent Reinforcement Learning (2019)4.03
• MADQRL: Distributed Quantum Reinforcement Learning Framework For Multi-agent Environments (2026)0.00
• A Further Exploration Of Deep Multi-agent Reinforcement Learning With Hybrid Action Space (2022)5.84