Implementation of recent and current state-of-the-art (as od 2017) Machine Learning algorithms with examples how to apply them to solve real problems from OpenAI website.
Solved environments:
- CartPole-v0
- CartPole-v1
- Breakout-v0
Used algorithms:
- Deep Q-Learning
- Double Deep Q-Learning
- Double Deep Q-Learning with Prioritized Experience Replay
- Monte-Carlo Policy Gradient (REINFORCE)
- Actor-Critic Policy Gradient
- Actor-Critic Policy Gradient with Baseline