Reinforcement Learning racing cars
Reinforcement Learning racing cars
Embedded Files
A race of autonomous cars driven by reinforcement learning. Several difficulty levels are developped illustrating different RL technique. Challenge behavior tree trained and PPO trained AIs. You can also train your own AI by recording your driving style. The imitation learning trained AI is capable of learning from the player's way of driving. Thanks to randomly generated circuits, each race is unique!
Developped during the UQAC Summer Session 2024.
Technologies Used :
Unreal Engine 5.4
C++
UE5 plugin : Learning Agents
SOLO PROJECT
SOLO PROJECT
RacingCars.mp4PPO trained AI cars
PPO trained AI cars
1sthour.mp41h trained cars
1h trained cars
EndTraining.mp43h trained cars
3h trained cars
TurboAIVideo.mp4IMPLEMENTATION On Simpler Games (Python)
IMPLEMENTATION On Simpler Games (Python)
Catcher
Cliff walking
Ice Walking
Taxi
Atelier_IA_II___Projet.pdfMy teammate : Basil Bourbayre
The complete code here :
Based on the papers :
1] Abid Ali Awan. An introduction to q-learning : A tutorial for beginners, Oct 2022.
[2] Epic. Unreal engine 5.3 learning agents plugin documentation, Sep 2023.
[3] Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antono-glou, Daan Wierstra, and Martin Riedmiller. Playing atari with deep reinforcement learning. arXiv preprint arXiv :1312.5602, 2013.
[4] Brendan Mulcahy. Unreal engine 5.3 learning to drive tutorial, Sep 2023.
[5] Matthias Plappert. keras-rl. https://github.com/keras-rl/keras-rl, 2016.
[6] Adi Aiman Bin Ramlan, Azliza Mohd Ali, Nurzeatul Hamimah Abdul Hamid, and Rozianawaty Osman. The implementation of reinforcement learning algorithm for ai bot in fighting video game. In 2021 4th International Symposium on Agents, Multi-Agent Systems and Robotics (ISAMSR), pages 96–100. IEEE, 2021.
[7] William Seymour. Training an ai to play a game using deep reinforcement learning, Sep 2023.
[8] Himanshu Singal, Palvi Aggarwal, and Varun Dutt. Modeling decisions in games using reinforcement learning. In 2017 International Conference on Machine Learning and Data Science (MLDS), pages 98–105. IEEE, 2017.
[9] Runjia Tan, Jun Zhou, Haibo Du, Suchen Shang, and Lei Dai. An modeling processing method for video games based on deep reinforcement learning. In 2019 IEEE 8th joint international information technology and artificial intelligence conference (ITAIC), pages 939–942. IEEE, 2019.
[10] Aaron Tucker, Adam Gleave, and Stuart Russell. Inverse reinforcement learning for video games. arXiv preprint arXiv:1810.10593, 2018.
Page updated
Google Sites
Report abuse