aadarshram commited on
Commit
6d403b1
·
verified ·
1 Parent(s): 9fe6e9b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -18,6 +18,7 @@ Trained for 3.5 hrs on T4 GPU on Colab free.
18
 
19
  The goal is to use this to compare ACTs performance on PushT against diffusion policy particularly the aspect of action multimodality.
20
 
 
21
 
22
  [Action Chunking with Transformers (ACT)](https://huggingface.co/papers/2304.13705) is an imitation-learning method that predicts short action chunks instead of single steps. It learns from teleoperated data and often achieves high success rates.
23
 
 
18
 
19
  The goal is to use this to compare ACTs performance on PushT against diffusion policy particularly the aspect of action multimodality.
20
 
21
+ Training logs: https://api.wandb.ai/links/ramachandranaadarsh-indian-institute-of-technology-madras/7m9dpcgw
22
 
23
  [Action Chunking with Transformers (ACT)](https://huggingface.co/papers/2304.13705) is an imitation-learning method that predicts short action chunks instead of single steps. It learns from teleoperated data and often achieves high success rates.
24