openai/Video-Pre-Training
Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos
PythonMIT
Issues
- 2
Rationale for KL decay
#44 opened by Rolv-Arild - 4
Access to youtube data labelled by the IDM
#42 opened by roger-creus - 1
Unable to install MineRL
#43 opened by Emericen - 2
GLFW Issue
#41 opened by ManuelCortes23 - 2
How can I make BASALT env in VPT
#37 opened by Zhoues - 1
- 1
SVM model release
#34 opened by nikepupu - 2
Question about action data form
#33 opened by zhufq00 - 1
gpu problem brand
#32 opened by Laz9999 - 2
- 1
Use Safetensors instead of Pickle
#30 opened by JD-The-65th - 4
Difficulty reproducing VPT inference validation loss with provided weights/data/code. Possible bug in behavioural_cloning.py?
#29 opened by GaPaLa - 1
- 1
Use of relative attention
#27 opened by florianleopold - 0
Ai VIDEO Pre Training
#28 opened by edwardemoryphotography - 1
TypeError: string indices must be integers
#25 opened by jhsul - 1
9 days on 720 GPUs?
#24 opened by jens321 - 1
Codebase for RL finteuning results in VPT paper
#23 opened by Ram81 - 7
Error on running the agent
#16 opened by fajrulfx - 6
Error running agents
#21 opened by Hema2-official - 6
Datasets seem to have 404 errors.
#13 opened by Coriana - 4
loading IDM weights without VPT's lib code?
#19 opened by verbose-void - 1
Training from scratch?
#11 opened by CrazyPython - 4
- 5
IDM Code
#4 opened by kevinzakka - 0
MacBook install issues
#10 opened by Alpslee - 1
- 3
Roadmap to improve
#6 opened by tanersekmen - 2
Running pip install git+https://github.com/minerllabs/minerl@v1.0.0 gives error
#7 opened by Snowplou - 1
Cannot download x3 or x1 models
#5 opened by NilaierMusic