Youtube-Code-Repository
Youtube-Code-Repository copied to clipboard
philtabor
Repository for most of the code from my YouTube channel
Remove the two params from constructor layer1_size=256, layer2_size=256 since not used in any part of the code.
Faster implementation for calculating q_target for training the DDDQN - in your video you mention the slow speed at which it runs. With this small change, it should run significantly...
Hello, I'm trying to start your Lunar_lander code, 'main_torch_dqn_lundar_lander.py' in 'archive' folder, but it is not started. The following is the error. Thank you. File "C:\Users\ys-th\Desktop\Spring2022\main_torch_dqn_lunar_lander.py", line 15, in env...
`magicSquares[resultingState]` should be changed to `self.magicSquares[resultingState]` https://github.com/philtabor/Youtube-Code-Repository/blob/33b1e4b4aaa453c31307d6bd4bb05e37ff24cb2b/ReinforcementLearning/Fundamentals/gridworld.py#L63
In the [line used to define the returns](https://github.com/philtabor/Youtube-Code-Repository/blob/1ef76059bf55f7df9ccc09fce0e0bfb7c13e89bd/ReinforcementLearning/PolicyGradient/PPO/torch/ppo_torch.py#L186), we use the GAE + values as the target for the critic to learn. Is this correct? My intuition says no --...
As mentioned in the video: https://youtu.be/LawaN3BdI00?t=1420 we don't need it.
I get this error: --------------------------------------------------------------------------- ValueError Traceback (most recent call last) in 26 score = 0 27 while not done: ---> 28 action = agent.choose_action(observation) 29 observation_, reward, done, info...
If I understand correctly, the code in [tensorflow2/actor_critic.py](https://github.com/philtabor/Youtube-Code-Repository/blob/master/ReinforcementLearning/PolicyGradient/actor_critic/tensorflow2/actor_critic.py) implements the `One-step Actor-Critic (episodic)` algorithm given on page 332 of RLbook2020 by Sutton/barto (picture given below).  Here we can see...
Hi, @philtabor ! Thanks for the awesome code and video! Those really help me to study and understand reinforcement learning. I found that the actor and critic model are not...
