Wiki Enseignement

User Tools

Site Tools

Trace:
learning:intro

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
learning:intro [2019/12/05 19:54] – orellearning:intro [2024/03/18 15:06] (current) – external edit 127.0.0.1
Line 10: Line 10:
  
   * http://ai.berkeley.edu/lecture_slides.html   * http://ai.berkeley.edu/lecture_slides.html
 +  * https://github.com/janishar/mit-deep-learning-book-pdf (MIT Book)
 +  * https://web.stanford.edu/class/psych209/Readings/SuttonBartoIPRLBook2ndEd.pdf (RL)
  
 === Intro à TensorFlow === === Intro à TensorFlow ===
Line 30: Line 32:
     * https://keon.io/deep-q-learning/     * https://keon.io/deep-q-learning/
     * https://medium.com/@gtnjuvin/my-journey-into-deep-q-learning-with-keras-and-gym-3e779cc12762     * https://medium.com/@gtnjuvin/my-journey-into-deep-q-learning-with-keras-and-gym-3e779cc12762
 +
 +=== Atari 2600 ===
 +
 +  * Playing Atari with Deep Reinforcement Learning, Deepmind.com (2013).
 +    * https://arxiv.org/pdf/1312.5602.pdf
 +  * Learning from the memory of Atari 2600 (2016).
 +    * https://deepsense.ai/playing-atari-on-ram-with-deep-q-learning/
 +    * https://github.com/sygi/deep_q_rl
 +    * https://cdn-sv1.deepsense.ai/wp-content/uploads/2016/09/1605.01335v1-4.pdf
   * DQN : Atari Breakout examples   * DQN : Atari Breakout examples
     * https://becominghuman.ai/lets-build-an-atari-ai-part-1-dqn-df57e8ff3b26     * https://becominghuman.ai/lets-build-an-atari-ai-part-1-dqn-df57e8ff3b26
Line 35: Line 46:
     * https://towardsdatascience.com/tutorial-double-deep-q-learning-with-dueling-network-architectures-4c1b3fb7f756     * https://towardsdatascience.com/tutorial-double-deep-q-learning-with-dueling-network-architectures-4c1b3fb7f756
     * https://github.com/andi611/DQN-Deep-Q-Network-Atari-Breakout-Tensorflow     * https://github.com/andi611/DQN-Deep-Q-Network-Atari-Breakout-Tensorflow
 +    * https://deepsense.ai/playing-atari-on-ram-with-deep-q-learning/
     * ...     * ...
   * Reinforcement Learning + Keras + Atari : https://github.com/rlcode/reinforcement-learning   * Reinforcement Learning + Keras + Atari : https://github.com/rlcode/reinforcement-learning
 +  * DDQN + Genetic
 +    * https://towardsdatascience.com/atari-reinforcement-learning-in-depth-part-1-ddqn-ceaa762a546f
 +    * https://towardsdatascience.com/atari-solving-games-with-ai-part-2-neuroevolution-aac2ebb6c72b
  
-=== Graph ===+=== About Graph ===
  
   * Graph Representation Learning: https://www.youtube.com/watch?v=YrhBZUtgG4E   * Graph Representation Learning: https://www.youtube.com/watch?v=YrhBZUtgG4E
 +  * GCN : https://towardsdatascience.com/how-to-do-deep-learning-on-graphs-with-graph-convolutional-networks-7d2250723780
 +  * https://rlgm.github.io/papers/41.pdf
 +  * Semi-Supervised Classification with Graph Convolutional Networks: https://arxiv.org/abs/1609.02907
  
 === Fun! === === Fun! ===
  
-  * https://github.com/greerviau/SnakeAI+  * https://github.com/greerviau/SnakeAI + https://www.youtube.com/watch?v=zIkBYwdkuTk
   * Alpha Toe   * Alpha Toe
     * https://github.com/DanielSlater/AlphaToe     * https://github.com/DanielSlater/AlphaToe
learning/intro.1575575697.txt.gz · Last modified: 2024/03/18 15:05 (external edit)