deep-reinforcement-learning
deep-reinforcement-learning copied to clipboard
udacity
Repo for the Deep Reinforcement Learning Nanodegree program
Show the differences in the mc backjack policy plot from the optimal policy. Just puts some little red X's on the graph which show where your blackjack policy deviates from...
Fan-in is defined to be the maximum number of inputs to a layer. The weight matrix is transposed. This means that the number of inputs are equal to the second...
* Use gymnasium instead of gym * Reflect interface change of env.reset and env.step * Enable rendering in Jupyter Notebook * Use CartPole-v1
* Use gymnasium==0.29.1 instead of gym * Reflect interface change of env.reset and env.step * Enable rendering in Jupyter Notebook * Remove unused import
* Use gymnasium instead of gym * Reflect interface change of env.reset and env.step * Enable rendering in Jupyter Notebook * Use CartPole-v1
This issue refers to the Navigation task [here](https://github.com/udacity/deep-reinforcement-learning/tree/master/p1_navigation) This won't work on Windows64, as the environment throws a timeout error and fails to produce the required 'env' object. Refer to...
The requirements.txt file includes torch==0.4.0 This throws an error as this version is not available any longer, also preventing the packages further down the list from being installed. 