search

Almujtaba-Yaseen / Learning-Reinforcement-Learning

Tracking my RL learning journey...
0 stars 0 forks source link

An issue regarding Learning-Reinforcement-Learning/my solutions to the exercises in dennybritz repo/MC/MC Prediction.ipynb #2

Open Almujtaba-Yaseen opened 2 years ago

Almujtaba-Yaseen commented 2 years ago

The exercise asked to implement the Monte Carlo Prediction to estimate state-action values... I implemented state values instead...

Will do the changes soon...

Almujtaba-Yaseen commented 2 years ago

Just discoverd that inside the exercise file, it asks to implement a function that returns the state value function V.

But it will be nice if you implemented a function that returns Q(s, a) as well...