MarcinPerka / FrozenLakeRL

Implementation of Reinforcement Learning temporal-differences methods in Frozen Lake environment.

Frozen Lake Reinforcement Learning

Implementation of Reinforcement Learning algorithms in Open AI Gym Frozen Lake environment (https://gym.openai.com/envs/FrozenLake-v0/)
Scripts uses temporal-differences methods:

• Q-Learning
• SARSA
• Deep Q-Learning
• Deep SARSA
• Deep Q-Learning with Target Network and Experience Replay
• Deep SARSA with Target Network and Experience Replay