Thomas Simonini

Awesome, thanks for the update I merge it 🤗

Hi, I'm planning to update the demo but I still have the issue. Is there is something I can change from my side implementation to solve the problem or it's...

No pb and it's not urgent don't worry 🤗. Let me know if/how I can help.

Hey there 👋 , So indeed there's a mistake here but for me it's that it should be max a' Q(St+1, a') a' indicates the best At+1 It's not supposed...

Ok, I cloned the repo. I can reduce some stuff, for instance the gifs. But most of my folders are 20mb because for instance for deep-rl-q-part1 we have 73 files...

Hi @micheljperez nice work! You're using the new version of Atari Environments (we use the former one for the Unit 4 tutorial). I was thinking to add this script for...

Thanks for the update. Before merging it we need to remove epsilon from Step 4: Create a model dictionary 💾 and publish our trained model on the Hub 🔥

Awesome thanks I merge it 🤗

Hey there 👋 , Thanks for the feedback and pointing it out. I'm agree it might be misleading. I'm adding it to the updates I'll need to make for the...

Thanks for the notebook tutorials for wandb and tensorboard I'm merging it to the repo 🤗