Skip to content

Various reinforcement learning algorithms implemented on the frozen lake grid world.

Notifications You must be signed in to change notification settings

Animesh-Chourey/Frozen-Lake

Repository files navigation

Various reinforcement learning algorithms are implemented to find policies for the frozen lake environment.

The following reinforcement learning algorithms have been implemented here:

  • Tabular model-based reinforcement learning
    • Policy Evaluation
    • Policy Improvement
    • Policy Iteration
    • Value Iteration
  • Tabular model-free reinforcement learning
    • Sarsa
    • Q-learning
  • Non-tabular model-free reinforcement learning
    • Linear Sarsa
    • Linear Q-learning