Jonathan Balloch
Jonathan Balloch
### 🚀 Feature Standardization of intrinsic rewards, and a single parameter to turn off extrinsic rewards ### Motivation Historically "rewards" have been modeled as being strictly intrinsic, per the theoretical...
Hey there! My research is taking me into NLP and I want to get sped up fast. Specifically I will be integrating natural language into my policy learning framework. There...
Minor issue, but worth mentioning: this library has no explicit requirements for FFMPEG, but recordings of the videos seem to depend pretty heavily on the `-crf` command (example: cell:4;line:6 in...
Do you all use unique code for baseline implementations of World Models (with AE and VAE) or do you use a publicly accessible library? Can you point me toward the...
Are there any current efforts/ roadmap items/ interest in moving acme and/or dm2gym to Farama Foundation Gymnasium?
I am trying to run YOLOX on my Jetson Nano with JetPack 4.6.3 using the the l4t-pytorch:r32.7.1-pth1.10-py3 image. However, it seems like this leads internal conflicts (specifically set off by...
What we should add is a feature that will split up into train, test, and validation, either by splitting the videos (better for testing dataset coverage) or more simply having...
you should advise Ubuntu 20.04+ users to install `libdbus-1-dev` before trying to make the venv from requirements and build the source, specifically with regards to the building of `dbus-python`: `sudo...