HydroShear Tactile RL
reinforcement learning checkpoints
1 min readupdated
This repository contains reinforcement learning (RL) policy checkpoints and linear probes for simulating contact-rich manipulation using the HydroShear tactile sensor. The initial release covers a peg-insertion experiment trained from scratch in Isaac Gym Preview. It includes actor and critic models alongside 245 linear probes for analyzing the network's internal representations. Useful for researchers and engineers working on tactile sensing and sim-to-real robotics simulation.
Key features
- Trains both the policy and privileged critic from scratch using PPO.
- 245 linear probes for predicting normal force, shear force, contact points, and slip velocity.
- Built on the Isaac Gym Preview simulator and the HydroShear tactile model.
- Includes milestone checkpoints, best-reward saves, and final weights.
What you can do
- Load the trained peg-insertion policy and run it inside the HydroShear research environment.
- Use the saved probe weights to analyze how the network internally represents tactile data.
- Download the full repository or just the subdirectories you need via the hf download CLI.
Example
Download only the files for the peg-insertion task:
hf download Tahuubinh/hydroshear-tactile-rl-checkpoints \
--include "peg_insertion/**" \
--include "manifests/peg_insertion_*" \
--local-dir hydroshear-peg-insertionRead more
DetailsSimulator: Isaac Gym Preview
Tactile observations: Two 9x7x2 shear force fields
Parallel environments: 256
Requested transitions: 150,000,000
License: MIT










Comments