A Collaborative Multiagent Reinforcement Learning Method Based on Policy Gradient Potential

Unsignalized intersection control is one of the most critical issues in intelligent transportation systems, which requires connected and automated vehicles to support more frequent information interaction and on-board computing. It is very promising to introduce reinforcement learning in the unsignalized intersection control. However, the existing multiagent reinforcement learning algorithms, such as multiagent deep deterministic policy gradient (MADDPG), hardly handle a dynamic number of vehicles, which cannot meet the need of the real road condition. Thus, this paper proposes a Cooperative MADDPG (CoMADDPG) for connected vehicles at unsignalized intersection to solve this problem. Firstly, the scenario of multiple vehicles passing through an unsignalized intersection is formulated as a multiagent reinforcement learning (RL) problem. Secondly, MADDPG is redefined to adapt to the dynamic quantity agents, where each vehicle selects reference vehicles to construct a partial stationary environment, which is necessary for RL. Thirdly, this paper incorporates a novel vehicle selection method, which projects the reference vehicles on a virtual lane and selects the largest impact vehicles to construct the environment. At last, an intersection simulation platform is developed to evaluate the proposed method. According to the simulation result, CoMADDPG can reduce average travel time by 39.28% compared with the other optimization-based methods, which indicates that CoMADDPG has an excellent prospect in dealing with the scenario of unsignalized intersection control.

Download Full-text

A Method of Personalized Driving Decision for Smart Car Based on Deep Reinforcement Learning

Information ◽

10.3390/info11060295 ◽

2020 ◽

Vol 11 (6) ◽

pp. 295 ◽

Cited By ~ 1

Author(s):

Xinpeng Wang ◽

Chaozhong Wu ◽

Jie Xue ◽

Zhijun Chen

Keyword(s):

Reinforcement Learning ◽

Decision Model ◽

Gradient Algorithm ◽

Learning Goals ◽

Learning Method ◽

Automatic Driving ◽

Proposed Model ◽

Policy Gradient ◽

Self Learning ◽

Better Than

To date, automatic driving technology has become a hotspot in academia. It is necessary to provide a personalization of automatic driving decision for each passenger. The purpose of this paper is to propose a self-learning method for personalized driving decisions. First, collect and analyze driving data from different drivers to set learning goals. Then, Deep Deterministic Policy Gradient algorithm is utilized to design a driving decision system. Furthermore, personalized factors are introduced for some observed parameters to build a personalized driving decision model. Finally, compare the proposed method with classic Deep Reinforcement Learning algorithms. The results show that the performance of the personalized driving decision model is better than the classic algorithms, and it is similar to the manual driving situation. Therefore, the proposed model can effectively learn the human-like personalized driving decisions of different drivers for structured road. Based on this model, the smart car can accomplish personalized driving.

Download Full-text

A Coordinated Multiagent Reinforcement Learning Method Using Chicken Game

2020 IEEE International Conference on Networking, Sensing and Control (ICNSC) ◽

10.1109/icnsc48988.2020.9238072 ◽

2020 ◽

Author(s):

Zihui Wang ◽

Zhi Wang ◽

Chunlin Chen

Keyword(s):

Reinforcement Learning ◽

Learning Method ◽

Multiagent Reinforcement Learning ◽

Chicken Game

Download Full-text

Reward-Free Reinforcement Learning Algorithm Using Prediction Network

Fuzzy Systems and Data Mining VI - Frontiers in Artificial Intelligence and Applications ◽

10.3233/faia200744 ◽

2020 ◽

Author(s):

Zhen Yu ◽

Yimin Feng ◽

Lijun Liu

Keyword(s):

Reinforcement Learning ◽

Learning Algorithm ◽

Value Functions ◽

Learning Method ◽

Reward Function ◽

Network Training ◽

Learning Tasks ◽

Reward Value ◽

Policy Gradient ◽

Reward Functions

In general reinforcement learning tasks, the formulation of reward functions is a very important step in reinforcement learning. The reward function is not easy to formulate in a large number of systems. The network training effect is sensitive to the reward function, and different reward value functions will get different results. For a class of systems that meet specific conditions, the traditional reinforcement learning method is improved. A state quantity function is designed to replace the reward function, which is more efficient than the traditional reward function. At the same time, the predictive network link is designed so that the network can learn the value of the general state by using the special state. The overall structure of the network will be improved based on the Deep Deterministic Policy Gradient (DDPG) algorithm. Finally, the algorithm was successfully applied in the environment of FrozenLake, and achieved good performance. The experiment proves the effectiveness of the algorithm and realizes rewardless reinforcement learning in a class of systems.

Download Full-text