Lorenzo Terenzi

Results 9 issues of Lorenzo Terenzi

The add_uid variable is not passed to the agent and learner, and is set to default to true in the Snapshotter and Checkpointer. Therefore when passing to the agent the...

The only customizable path is the checkpointer saving path, rest is set to default to ~/acme

The main runs on pytorch 0.4.1 but it fails for pytorch 1.6.0. Running the main.py for VAIL implementation I get a runtime error about a replacement in place of a...

added feature to save map in a specified ref frame

Introduces new functionality to: - new msgs to use the nav msg as target goal - possible inconstistency if breking distance does not match with nominal vel and acc -...

I was wondering if there are any plans to release multi-gpu training code? Naively pmapping and using DDPPO does not seem to scale well, as the gpus remain idle while...

Hi thanks for the contribution, I was trying to find where you extract the query voxels and associate them across frames, but I can't find it in the code. Could...

Any plans to also upload the fine-tuned sonata checkpoints for the indoor/outdoor scenes like has been done with point transformer v3?

## Summary This PR introduces a unified mount configuration system for Docker containers and enhances cluster deployment workflows, making it easier to develop with external IsaacLab/RSL-RL installations and deploy to...