Skip to content
Other

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-insertion
Read moreDetails
Simulator: Isaac Gym Preview
Tactile observations: Two 9x7x2 shear force fields
Parallel environments: 256
Requested transitions: 150,000,000
License: MIT
Discuss Telegram 0

Will it run?

Working out the memory needs

The bot is still collecting this model's weight sizes; the estimate will appear here in a few minutes. Meanwhile you can rent a GPU with headroom.

Massed ComputeOpen Massed Compute

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # Tahuubinh/hydroshear-tactile-rl-checkpoints
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download Tahuubinh/hydroshear-tactile-rl-checkpoints --local-dir ~/models/hydroshear-tactile-rl-checkpoints
    # The model is in ~/models. How to run it is in the model card (link above).
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of hydroshear-tactile-rl-checkpoints (quants, finetunes, LoRAs) will show up under the bell.

No known relatives of this model yet. All derivatives on Hugging Face

About the model

Tahuubinh/hydroshear-tactile-rl-checkpoints
Author
Tahuubinh
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

00

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments