雖然樹莓派 3B+ 可以跑 Denny Britz 所寫的

reinforcement-learning/TD/

Model-Free Prediction & Control with Temporal Difference (TD) and Q-Learning

Learning Goals

• Understand TD(0) for prediction
• Understand SARSA for on-policy control
• Understand Q-Learning for off-policy control
• Understand the benefits of TD algorithms over MC and DP approaches
• Understand how n-step methods unify MC and TD approaches
• Understand the backward and forward view of TD-Lambda

 

筆記本︰

 

但是跑不了

reinforcement-learning/DQN/

Deep Q-Learning

Learning Goals

• Understand the Deep Q-Learning (DQN) algorithm
• Understand why Experience Replay and a Target Network are necessary to make Deep Q-Learning work in practice
• (Optional) Understand Double Deep Q-Learning
• (Optional) Understand Prioritized Experience Replay

 

呦！

………

 反思 DQN 動則需要好幾 G  記憶體，怕也太為難小樹莓了吧☺