-
Hi
May I ask the setting about td3_bc on antmaze. I find current hyperparameters can not work well and obtain a similar result as in the paper.
Best
-
Please add crate to category: Neural Networks
If you're open to multiple categories, I think dfdx could also be added to Reinforcement Learning (I have some examples of a Deep Q Network and Proxima…
-
## 🚀 Feature
Dear community,
As PyTorch Lightning mature, we believe it is important for the Lightning Team and its community to improve the Lightning onboarding process.
In that regards…
-
I have just gone through the paper "PowerGym: A Reinforcement Learning Environment for Volt-Var Control in Power Distribution Systems". I have found it insightful and thanks for sharing this reposito…
-
I'm using the gpt2-sentiment.py script in examples for distributed training, where the data and reward models are replaced with our own.
If there is no problem with using a GPU for training, it can…
-
I will progressively summarize talks I find illuminating from the [Stanford MLSys](https://mlsys.stanford.edu/) Seminar Series here.
Talk Link: [https://www.youtube.com/watch?v=DB7oOZ5hyrE](https://w…
-
Update:
Seems that I got stuck at `stats_to_np`.
Hi, I encountered the same problem, where I got stuck at `gather_stats`. But I am using the official script as shown below. Could you help me take …
-
Hello
Thank you for sharing your materials!
And I am very happy with your modified Flow. In the past, I tried to install Flow from the official repo but it always had errors. With your repo, it is e…
-
https://mp.weixin.qq.com/s/DAPirChUTKZ9yLExJw86Tg
-
Hi, I'm new to wandb and is running code in [ppo-implementation-details](https://github.com/vwxyzjn/ppo-implementation-details) following the video tutorial [Part 1 of 3 — Proximal Policy Optimization…