/rl_algorithms

reinforcement learning algorithms implementation. custom opencv based environment to test codes.

Primary LanguageJupyter Notebook

Reinforcement Learning

Reinforcement learning algorithms implementation. Custom OpenCV based environment to test codes.

Implemented Algorithms:

  • Value Iteration
  • Policy Iteration
  • Q-Learning
  • Deep Q-Learning
  • Vanilla Policy Gradient - REINFORCE
  • A2C
  • A3C
  • PPO
  • DDPG

Results

Value and Policy Iteration

Method Deterministic Frozen Lake Stochastic Frozen Lake
Value Iteration 7 8
Policy Iteration 7 3
Q-Learning

Deep Q-Learning