Multi-agent Deep Reinforcement Learning for Charge-sustaining Control of Multi-mode Hybrid Vehicles.
Min HuaQuan ZhouCetengfei ZhangHongming XuWei LiuPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- multi agent
- control problems
- optimal control
- traffic signal control
- state space
- robot control
- control system
- control policy
- autonomous vehicles
- function approximation
- traffic signal
- real time
- reinforcement learning algorithms
- action selection
- adaptive control
- multiagent systems
- learning agents
- receding horizon
- model free
- control method
- control strategies
- unmanned aerial vehicles
- optimal policy
- cooperative
- learning algorithm
- control strategy
- markov decision processes
- multi agent reinforcement learning
- policy search
- machine learning