Q Learning
concepts · 3 notes linked
Related: Reinforcement Learning · Meta Reinforcement Learning · Off Policy Learning · Openai · Deepmind · Policy Gradient · Model Based RL · Github
Notes
- Flappy Bird RL — Q-learning agent trained to play Flappy Bird in JavaScript
- Meta-Q-Learning — Off-policy meta-RL via Q-learning with trajectory context variable
- Reinforcement Learning algorithms — an intuitive overview — Survey of model-free and model-based RL algorithm families