Skip to content
/ Obstacle_avoidance_dqn Public

Obstacle avoidance with DQN Algorithm (Double DQN, Prioritized Experience Replay, Dueling Network Architectures, N-step Return, Soft TargetNet, Parallel computing...

5 stars 0 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

saaries/Obstacle_avoidance_dqn

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
img
img
 
 
keras_tensorflow_log
keras_tensorflow_log
 
 
logs
logs
 
 
utils
utils
 
 
weights_saved
weights_saved
 
 
README.md
README.md
 
 
env1.py
env1.py
 
 
environment.py
environment.py
 
 
img2vdo.py
img2vdo.py
 
 
output_logs.txt
output_logs.txt
 
 
report.pdf
report.pdf
 
 
result_demo.gif
result_demo.gif
 
 
train_dqn_v2.py
train_dqn_v2.py
 
 
train_dqn_v3.py
train_dqn_v3.py
 
 

Repository files navigation

Obstacle_avoidance_dqn

In the given environment, the agent/white dot need to avoid collision with obstacles/black dots.

About

Obstacle avoidance with DQN Algorithm (Double DQN, Prioritized Experience Replay, Dueling Network Architectures, N-step Return, Soft TargetNet, Parallel computing...

Topics

reinforcement-learning parallel-computing obstacle-avoidance double-dqn dqn-tensorflow

Resources

Readme
Activity

Stars

5 stars

Watchers

2 watching

Forks

0 forks
Report repository

Releases

No releases published

Packages

No packages published

Languages