Skip to content

Accepted by AROB 2021. For letting agents in traffic simulation behave more like humans, we propose a unified mechanism for agents learn to decide various accelerations on deep reinforcement learning and generate a traffic flow behaving variously to simulate the real traffic flow.

Notifications You must be signed in to change notification settings

ZHONGJunjie86/Generating-Traffic-Flows-with-MARL

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

17 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Generating-Traffic-Flows-with-MARL

Accepted by AROB 2021

Find my paper Generation of Traffic Flows in Multi-Agent Traffic Simulation with Agent Behavior Model based on Deep Reinforcement Learning.

Abstract

In multi-agent based traffic simulation, agents are always supposed to move following existing instructions, and mechanically and unnaturally imitate human behaviour. The human drivers perform acceleration or deceleration irregularly all the time, which seems unnecessary in some conditions. For letting agents in traffic simulation behave more like humans and recognize other agents’ behaviour in complex conditions, we propose a unified mechanism for agents learn to decide various accelerations by using deep reinforcement learning based on a combination of regenerated visual images revealing some notable features, and numerical vectors containing some important data such as instantaneous speed. By handling batches of sequential data, agents are enabled to recognize surrounding agents’ behaviour and decide their own acceleration. In addition, we can generate a traffic flow behaving diversely to simulate the real traffic flow by using an architecture of fully decentralized training and fully centralized execution without violating Markov assumptions.

Feature extraction and image inverse generation

image image image image image image image image image image

TD

MC

Actor Critic (TD)

 

About GAMA

 The GAMA is a platefrom to do simulations.

About

Accepted by AROB 2021. For letting agents in traffic simulation behave more like humans, we propose a unified mechanism for agents learn to decide various accelerations on deep reinforcement learning and generate a traffic flow behaving variously to simulate the real traffic flow.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published