ZHONG Junjie's repositories
Mixed_Input_PPO_CNN_LSTM_Car_Navigation
Accepted by AROB 2021. A car-agent navigates in complex traffic conditions by Mixed_Input_PPO_CNN_LSTM model.
Generating-Traffic-Flows-with-MARL
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.
A2C-LSTM-TD-single-car-intersection
A model used to identify the usefulness of LSTM with sequential data.
PPO_LSTM_Car_Navigation
A car-agent navigates in complex traffic conditions by PPO.
A2C-TD-single-car-intersection
A model describing how a car learns to control its acceleration by A2C_TD.
A2C-MC-single-car-intersection
This is a model describing a car runs to goal in limited time with A2C-MC algorithm.
GithubTutorial
Githubのチュートリアル資料です。
Modeling-Others-as-a-Player-MOP
Accepted by Proceedings of 24th International Conference on Engineering Applications of Neural Networks (EANN 2023, which will be renamed to Engineering Applications and Advances of Artificial Intelligence, EAAAI 2023)
Influential-Communication
From paper: Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning. Not the same one.
MADDPG_MNIST
Use MADDPG to handle the MNIST.