GitHub - jlabhishek/ObstacleAvoidanceWithQ-Learning: Obstacle Avoidance Bot training on V-rep using Q learning Algorithm. Neural Networks were used as function approximator for state space

jlabhishek / ObstacleAvoidanceWithQ-Learning Public

Notifications You must be signed in to change notification settings
Fork 1
Star 7

Obstacle Avoidance Bot training on V-rep using Q learning Algorithm. Neural Networks were used as function approximator for state space

7 stars 1 fork Branches Tags Activity

Star

Notifications

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 4 Commits
Files		Files
__pycache__		__pycache__
pioneer_qlearn_deep		pioneer_qlearn_deep
Path_modified2.ttt		Path_modified2.ttt
complexCommandTest.py		complexCommandTest.py
deepQ.py		deepQ.py
driver.py		driver.py
environment.py		environment.py
graph.py		graph.py
graph_mav.py		graph_mav.py
nn_q.py		nn_q.py
pathPlanningTest.py		pathPlanningTest.py
qAgent.py		qAgent.py
qEnvironment.py		qEnvironment.py
q_learn.py		q_learn.py
q_table_list.pickle		q_table_list.pickle
readMe.txt		readMe.txt
remoteApi.so		remoteApi.so
simpleSynchronousTest.py		simpleSynchronousTest.py
simpleTest.py		simpleTest.py
square_bot_bothTurns_cam_collision.ttt		square_bot_bothTurns_cam_collision.ttt
square_train.ttt		square_train.ttt
vrep.py		vrep.py
vrepConst.py		vrepConst.py

Repository files navigation

Make sure you have following files in your directory, in order to run the various examples:

1. vrep.py
2. vrepConst.py
3. the appropriate remote API library: "remoteApi.dll" (Windows), "remoteApi.dylib" (Mac) or "remoteApi.so" (Linux)
4. simpleTest.py (or any other example file)