leehe228 / logisticsenv

UAV Logistics Environment for Multi-Agent Reinforcement Learning / Unity ML-Agents / Unity 3D

😀 안녕하세요! 반갑습니다 제 깃허브를 방문해주셔서 감사합니다.
저는 AI Researcher를 꿈꾸며 AI 대학원 진학을 목표로 공부중인 이호은 (Hoeun Lee) 입니다.

🏫 충남삼성고등학교 IT디플로마를 졸업하고 (2017/3 ~ 2020/2),
🏢 건국대학교 컴퓨터공학부 20학번으로 입학하여, 3학년에 재학중이며 (2020/3 ~),
🎓 2025년 8월 졸업 후, AI(인공지능) 대학원 진학을 목표로 공부중입니다.
🔬 내년 가을학기 석박통합과정 입학을 목표로 2024년 6월부터 서울대학교 전기∙정보공학부 AIDAS LAB 학부연구인턴으로 공부하고 있습니다.
🌟 AI 기술을 기반으로 사회 구성원의 삶을 개선하고, 모두가 공평하게 더 나은 삶을 누릴 수 있는 세상을 만드는 것이 저의 꿈입니다.

🔍 아직은 연구 분야를 폭넓게 탐색하고 있으며, 관심 있는 연구 분야는
Generative AI, Multi-Modal AI, Large Model, On-Device AI, AI for System, Deep Reinforcement Learning 입니다.

자세한 이력서와 성적은 CV / Transcript에서 확인하실 수 있습니다.
CV보다 제 이력을 보기 좋게 정리한 페이지입니다.
혹시, 링크드인을 하고 계시다면 편하게 1촌 신청을 걸어주시면 감사드리겠습니다. →

관련 웹페이지 리스트입니다.

• 

• 

• 

Languages

AI/ML Tools

Development

etc

✉️ Contact me → [email protected]

logisticsenv's Issues

Agents Not Acting Autonomously in MAAC and MAPPDG Implementations

Hello,I am greatly appreciative of your valuable work.While I have some questions.
I have successfully set up the environment following your documentation and am able to run the main.py files for MAAC and MAPPDG. However, while the program is running, I observe through the displayed window that the agents do not seem to be acting autonomously. I am wondering what could be the reason for this, and how I can enable the agents to act on their own.

Could you please provide any suggestions or guidance on this matter? I would greatly appreciate your assistance in troubleshooting this issue. Thank you in advance for your time and expertise.

I am going to provide trained model file

Thank you to those of you who are very interested in my research and code.

Currently, there is a problem with the GPU server I was using, so I am in the process of training again after reset the server.
I will provide you with the trained model file after I finish training.

Thank you😊

Question about step() in gymwrapper5

Very awesome work! While I have some question
According to ML-agents, terminal steps contain information about agents which facing the final step. I found the t_s in your code is not used.
And another question, is the file gymwrapper5 indeed utilized gym wrapper of unity? I remember a doc in unity, saying gym wrapper in unity is not supported multi agents

Could I have your trained model?

Excuse me, may I respectfully ask if it would be possible for you to share your trained model model.pt files with me? My computer's performance is not quite good.

I would be extremely grateful for your help. Thanks! And your paper is awesome!

Build for windows

Hello Sir,
I am trying to run your code on windows, can you please help which path I shall give for Build_windows. I am totally lost, thanks

Question about Logistics.x86_64 in Build_Linux

Sorry to bother you, when I reproduced your code, the error： mlagents_envs.exception.UnityEnvironmentException: Environment shut down with return code 1. During my search for errors, I found that when the Logistics.x86_64 file was automatically generated , this error will disappear. Please tell me how to generate your Logistics.x86_64 file.