This repository contains a collection of reinforcement learning algorithms.

• FrozenLake-v0_Q_table - An implementation of Q-learning using tables to solve the FrozenLake-v0 problem.

• FrozenLake-v0_Q_network - An implementation of Q-learning using feed-foward NN to solve the FrozenLake-v0 problem.

• CartPole-v0_PG - An implementation of a neural network policy-gradient for the CartPole-v0 problem.

• CartPole-v0_model_based_RL An implementation of a neural network policy-gradient for the CartPole-v0 problem. Two networks are included: model network and policy network. https://gym.openai.com/evaluations/eval_9niu4HNZTgm0VLJ0b8MUtA#reproducibility