tdl.sh

# Temporal Difference Learning
# Reinforcement Learning
# Deep Q-Learning
# Experience Replay
# State, Action, Reward Triples
# TDLambda (Temporal Difference Learning, Monte Carlo) and or Dynamic Programming
# mac xcode-select --install
# mac pip install numpy incremental
# mac brew install golang libjpeg-turbo swig
# mac sudo -H pip3 install cmake
# mac export SDKROOT=/Applications/Xcode.app/Contents/Developer


sudo -H pip3 install cmake 
sudo apt install zlib1g-dev swig
sudo -H pip3 install gym[all]
# Hyperparameters (learning rate, discount rate, epsilon, feature extraction, nn architecture)
# Model the system (state, environment, actions, rewards, returns, episodes, discounting, policies, value functions)
# Convolutional Neural Networks, Recurrent Neural Networks, Regression, Classification, Generative Adversarial Networks, Autoencoders

# Markov Decision Process
#Set of all states, set of all actions, Set of all rewards, state transition probabilities, discount factor (gamma)