Reinforcement Learning - Implementation of Algorithms

Repo for RL Algorithms on Gym and Custom environments.

• Bandits Exploration

  • Thompson Sampling
  • Softmax
  • E-Greedy
  • Greedy

• Policy Iteration Vs Value Iteration

  • Frozen Lake
  • Taxi

• Feature Tiling with TD-Lambda

  • Continous Random Walk

• SARSA, Q-Learning, Expected SARSA

  • Cartpole

• Baird Triad

  • Implementation

• Actor-Critic Vs Reinforce

  • Cartpole