Pinned Repositories
traffic-simulator-Q-learning
We propose a driver modeling process and its evaluation results of an intelligent autonomous driving policy, which is obtained through reinforcement learning techniques. Assuming a MDP decision making model, Q-learning method is applied to simple but descriptive state and action spaces, so that a policy is developed within limited computational load. The driver could perform reasonable maneuvers, like acceleration, deceleration or lane-changes, under usual traffic conditions on a multi-lane highway. A traffic simulator is also construed to evaluate a given policy in terms of collision rate, average travelling speed, and lane change times. Results show the policy gets well trained under reasonable time periods, where the driver acts interactively in the stochastic traffic environment, demonstrating low collision rate and obtaining higher travelling speed than the average of the environment. Sample traffic simulation videos are postedsit on YouTube.
bayes-by-backprop
Implementing Bayes by Backprop with PyTorch. Applied on time-series prediction.
CoordinationGraphMARL
cs224n-stanford-winter2021
Stanford Winter 2021
DeepCorrectionCAS
Deep Corrections through DQN for Collision Avoidance Systems
deeplabv3plus_on_Mapillary_Vistas
Semantic Segmentation on the Mapillary Vistas Dataset
DICG
Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learning
gym
My own edition of OpenAI gym
Q-Learning-for-Intelligent-Driver
We propose a driver modeling process of an intelligent autonomous driving policy, which is obtained through Q-learning.
DICG
Deep Implicit Coordination Graphs
parachutel's Repositories
parachutel/cs224n-stanford-winter2021
Stanford Winter 2021
parachutel/deeplabv3plus_on_Mapillary_Vistas
Semantic Segmentation on the Mapillary Vistas Dataset
parachutel/Q-Learning-for-Intelligent-Driver
We propose a driver modeling process of an intelligent autonomous driving policy, which is obtained through Q-learning.
parachutel/CoordinationGraphMARL
parachutel/bayes-by-backprop
Implementing Bayes by Backprop with PyTorch. Applied on time-series prediction.
parachutel/DICG
Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learning
parachutel/DeepCorrectionCAS
Deep Corrections through DQN for Collision Avoidance Systems
parachutel/gym
My own edition of OpenAI gym
parachutel/traj_prediction
parachutel/back_to_china_pac
parachutel/backChina_conf
parachutel/baselines
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
parachutel/ConflictAvoidanceDASC
Conflict avoidance algorithm for unmanned aircraft traffic management
parachutel/cs221
parachutel/doubi
一个逗比写的各种逗比脚本~
parachutel/garage
A toolkit for reproducible reinforcement learning research
parachutel/git.cheatsheet
parachutel/MADRL
Repo containing code for multi-agent deep reinforcement learning (MADRL).
parachutel/models
Models and examples built with TensorFlow
parachutel/parachutel.github.io
Website Host
parachutel/restore-terminals-vscode
A VSCode extension to restore/startup terminals with a custom configuration
parachutel/Resume-and-CV
parachutel/teddysunss
https://github.com/teddysun/shadowsocks_install
parachutel/vscode-boxythemekit
My port of Sublime Boxy Themes to VSCode