hl-gauss-pytorch

HL Gauss - Pytorch

The Gaussian Histogram Loss (HL-Gauss) proposed by Imani et al. with a few convenient wrappers, in Pytorch.

A team at Deepmind wrote a paper with a lot of positive findings for its use in value-based RL.

Put into action here, seems to work well

Install

$ pip install hl-gauss-pytorch

Usage

The HLGaussLoss module as defined in Appendix A. of the Stop Regressing paper

import torch
from hl_gauss_pytorch import HLGaussLoss

hl_gauss = HLGaussLoss(
    min_value = 0.,
    max_value = 5.,
    num_bins = 32,
    sigma = 0.5,
    clamp_to_range = True # this was added because if any values fall outside of the bins, the loss is 0 with the current logic
)

logits = torch.randn(3, 16, 32).requires_grad_()
targets = torch.randint(0, 5, (3, 16)).float()

loss = hl_gauss(logits, targets)
loss.backward()

# after much training

pred_target = hl_gauss(logits) # (3, 16)

For a convenient layer that predicts from embedding to logits, import HLGaussLayer

import torch
from hl_gauss_pytorch import HLGaussLayer

hl_gauss_layer = HLGaussLayer(
    dim = 256, # input embedding dimension
    hl_gauss_loss = dict(
        min_value = 0.,
        max_value = 5.,
        num_bins = 32,
        sigma = 0.5,
    )
)

embed = torch.randn(7, 256)
targets = torch.randint(0, 5, (7,)).float()

loss = hl_gauss_layer(embed, targets)
loss.backward()

# after much training

pred_target = hl_gauss_layer(embed) # (7,)

For ablating the proposal, you can make the HLGaussLayer fall back to regular regression by setting use_regression = True, keeping the code above unchanged

HLGaussLayer(..., use_regression = True)

Citations

@article{Imani2024InvestigatingTH,
    title   = {Investigating the Histogram Loss in Regression},
    author  = {Ehsan Imani and Kai Luedemann and Sam Scholnick-Hughes and Esraa Elelimy and Martha White},
    journal = {ArXiv},
    year    = {2024},
    volume  = {abs/2402.13425},
    url     = {https://api.semanticscholar.org/CorpusID:267770096}
}

@inproceedings{Imani2018ImprovingRP,
    title   = {Improving Regression Performance with Distributional Losses},
    author  = {Ehsan Imani and Martha White},
    booktitle = {International Conference on Machine Learning},
    year    = {2018},
    url     = {https://api.semanticscholar.org/CorpusID:48365278}
}

@article{Farebrother2024StopRT,
    title   = {Stop Regressing: Training Value Functions via Classification for Scalable Deep RL},
    author  = {Jesse Farebrother and Jordi Orbay and Quan Ho Vuong and Adrien Ali Taiga and Yevgen Chebotar and Ted Xiao and Alex Irpan and Sergey Levine and Pablo Samuel Castro and Aleksandra Faust and Aviral Kumar and Rishabh Agarwal},
    journal = {ArXiv},
    year   = {2024},
    volume = {abs/2403.03950},
    url    = {https://api.semanticscholar.org/CorpusID:268253088}
}

Metadata

Release files for hl-gauss-pytorch 0.3.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for hl-gauss-pytorch 0.3.0
File	Size	Uploaded
hl_gauss_pytorch-0.3.0.tar.gz	9.2 kB	Sep 2, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for hl-gauss-pytorch 0.3.0
File	Interpreter	ABI	Platform	Reset
hl_gauss_pytorch-0.3.0-py3-none-any.whl 10.1 kB Sep 2, 2026	Python 3	none	any	Details

Total release size: 19.4 kB

Release files / hl_gauss_pytorch-0.3.0.tar.gz

Download URL	hl_gauss_pytorch-0.3.0.tar.gz
Size	9.2 kB
Tags	Source
SHA-256 checksum How to use checksums	`b750724f72cd9932340ff0eb2a3df634c415ed688b99718725daeb4784151175`
BLAKE2b-256 checksum How to use checksums	`7af783e84d91320aa0c8fa123387221659add62ff7dd7bd48dfd3e39aa3f3f6b`
Upload date	Sep 2, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`uv/0.8.17`

Release files / hl_gauss_pytorch-0.3.0-py3-none-any.whl

Download URL	hl_gauss_pytorch-0.3.0-py3-none-any.whl
Size	10.1 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`d0829cde029130bb308c332cd912f5cb05b791fb334a204e6b0330321f8341a1`
BLAKE2b-256 checksum How to use checksums	`f53901ee52f2ade8088d8d329a7d20f9d9adf375fdb08b70b1ab6be217545ad4`
Upload date	Sep 2, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`uv/0.8.17`