README.md

Reinforcement Learning (RL)

Reinforcement learning is a machine learning training method based on rewarding desired behaviors and/or punishing undesired ones. In general, a reinforcement learning agent is able to perceive and interpret its environment, take actions and learn through trial and error.

Subsets of Reinforcement Learning:

best way is to learn is from TOP to BOTTOM.

• Q-Learning
• Deep Q-Learning
• Double Deep Q-Learning
• Actor Critic Methods (not a network)
• Deep Deterministic Policy Gradient
• Proximal Policy Pptimization

Resources:

• https://www.youtube.com/watch?v=aIsgJJYrlXk
• https://www.davidsilver.uk/teaching/
• http://incompleteideas.net/book/RLbook2018.pdf
• https://www.ai.rug.nl/~mwiering/Intro_RLBOOK.pdf
• https://torres.ai/deep-reinforcement-learning-explained-series/
• https://www.tensorflow.org/agents/tutorials/0_intro_rl
• https://web.stanford.edu/class/psych209/Readings/MnihEtAlHassibis15NatureControlDeepRL.pdf
• https://github.com/germain-hug/Deep-RL-Keras
• https://www.youtube.com/watch?v=XjsY8-P4WHM