/RL_fall

Primary LanguageJupyter Notebook

YAI-6th fall RL study

studying with...

  1. my notes on Standford Lecture CS234
  2. Reinforcement Learning: An Introduction (2nd) - Sutton and Barto
  3. Papers related to the topic
  4. And code referenced for each topic :)
  5. ROBOTIS e-Manual TURTLEBOT3 Machine Learning (DQN D3QN PER ACER)

fall_week_1: SARSA and Q-learning

References

https://github.com/hunkim/ReinforcementZeroToAll
https://github.com/podondra/gym-gridworlds/tree/master/gym_gridworlds
https://github.com/minsuk-heo/kaggle-titanic

References

https://github.com/philtabor/Youtube-Code-Repository/tree/master/ReinforcementLearning/DeepQLearning https://github.com/seungeunrho/minimalRL

fall_week_3: Double, Dueling, Prioritized Experience Replay with DQN

References

https://www.youtube.com/watch?v=A39cjchWnsU
https://github.com/philtabor/Youtube-Code-Repository/tree/master/ReinforcementLearning/DeepQLearning

fall_week_4: Asynchronous Advantage Actor Critic A3C

References

https://github.com/seungeunrho/minimalRL/blob/master/a3c.py

fall_week_5 ~ 6: Installing and Establishing ROS / Gazebo Environment for TURTLEBOT3 machine learning

References

https://pinkwink.kr/1181
http://wiki.ros.org/noetic/Installation/Ubuntu
https://www.notion.so/b67ed727aea4467cbc3226bb0c8e8336
https://conservative-vector.tistory.com/entry/docker%EC%97%90%EC%84%9C-%EC%BB%A8%ED%85%8C%EC%9D%B4%EB%84%88-gui-%EC%8B%A4%ED%96%89%ED%95%98%EA%B8%B0
https://eungbean.github.io/2018/11/19/EOD-Gtk-WARNING-cannot-open-display/
http://wiki.ros.org/kinetic/Installation/Ubuntu
http://wiki.ros.org/ROS/Tutorials/InstallingandConfiguringROSEnvironment
https://emanual.robotis.com/docs/en/platform/turtlebot3/machine_learning/

fall_week_7~9: How to improve DQN? : D3QN / PER / and changing the Environment (+ Pushing Docker Image)

References

https://github.com/ROBOTIS-GIT/turtlebot3_machine_learning
https://github.com/Parsa33033/Deep-Reinforcement-Learning-DQN/blob/master/DQN-with-Prioritized-Experience-Replay.py#L34
https://github.com/kachayev/fn.py/pull/14/commits/391824c43fb388e0eca94e568ff62cc35b543ecb
https://stackoverflow.com/questions/58915023/what-is-an-alternative-method-of-using-random-choices-in-python-3-5
https://github.com/python/cpython/blob/0eaf7b975bd61169a8d78945d2d12f23299f61a8/Lib/random.py#L344

fall_week_10: Switching from DQN to ACER

References

https://github.com/openai/baselines/blob/master/baselines/acer/acer.py
https://github.com/seungeunrho/minimalRL/blob/master/acer.py
https://wwiiiii.tistory.com/entry/ACER-Sample-Efficient-ActorCritic-With-Experience-Replay
https://talkingaboutme.tistory.com/entry/RL-Policy-Gradient-Algorithms