Data

Tools

Indexes

Applications

Experiments

Open Source Science

irl-maxent

Maximum Entropy and Maximum Causal Entropy Inverse Reinforcement Learning Implementation in Python

https://github.com/qzed/irl-maxent

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (9.7%) to scientific vocabulary

Keywords

inverse-reinforcement-learning machine-learning maximum-entropy
Last synced: 6 months ago · JSON representation ·

Repository

Maximum Entropy and Maximum Causal Entropy Inverse Reinforcement Learning Implementation in Python

Basic Info
  • Host: GitHub
  • Owner: qzed
  • License: mit
  • Language: Jupyter Notebook
  • Default Branch: master
  • Homepage:
  • Size: 1.34 MB
Statistics
  • Stars: 293
  • Watchers: 4
  • Forks: 63
  • Open Issues: 3
  • Releases: 0
Topics
inverse-reinforcement-learning machine-learning maximum-entropy
Created almost 7 years ago · Last pushed almost 2 years ago
Metadata Files
Readme License Citation

README.md

Maximum Entropy Inverse Reinforcement Learning

This is a python implementation of the Maximum Entropy Inverse Reinforcement Learning (MaxEnt IRL) algorithm based on the similarly named paper by Ziebart et al. and the Maximum Causal Entropy Inverse Reinforcement Learning (MaxCausalEnt IRL) algorithm based on his PhD thesis. Project for the Advanced Seminar in Imitation Learning, summer term 2019, University of Stuttgart.

This implementation is available as python package at https://pypi.org/project/irl-maxent/ and can be installed via pip install irl-maxent. You may also want to have a look at the accompanying presentation.

For an example demonstrating how the Maximum (non-causal) Entropy IRL algorithm works, see the corresponding Jupyter notebook (notebooks/maxent.ipynb). Note that the provided python files (src/) contain a slightly more optimized implementation of the algorithms.

To run a demonstration without the notebook, you can directly run ./src/example.py. Also have a look at this file on how to use the provided framework. The framework contains: - Two GridWorld implementations for demonstration (irl_maxent.gridworld) - The algorithm implementations (irl_maxent.maxent) - A gradient based optimizer framework (irl_maxent.optimizer) - Plotting helper functions (irl_maxent.plot) - A MDP solver framework, i.e. value iteration and corresponding utilities (irl_maxent.solver) - A trajectory/trajectory generation framework (irl_maxent.trajectory)

This project solely relies on the following dependencies: numpy, matplotlib, itertools, and pytest.

Owner

  • Name: Maximilian Luz
  • Login: qzed
  • Kind: user
  • Location: Freiburg i. Br., Germany

PhD Student at the Robot Learning Lab, University of Freiburg.

Citation (CITATION.cff) 

cff-version: 1.2.0
title: Maximum Entropy Inverse Reinforcement Learning - An Implementation
message: 'If you use this software, please cite it as below.'
type: software
authors:
  - family-names: Luz
    given-names: Maximilian
    orcid: 'https://orcid.org/0000-0002-1123-6604'
    email: m@mxnluz.io
url: 'https://github.com/qzed/irl-maxent'
license: MIT
version: 0.1.0
date-released: '2019-07-01'

GitHub Events

Total
  • Watch event: 71
  • Fork event: 7
Last Year
  • Watch event: 71
  • Fork event: 7

Committers

Last synced: 9 months ago

All Time
  • Total Commits: 106
  • Total Committers: 2
  • Avg Commits per committer: 53.0
  • Development Distribution Score (DDS): 0.009
Past Year
  • Commits: 0
  • Committers: 0
  • Avg Commits per committer: 0.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
qzed q****d 105
Daniel Boateng 9****J 1

Issues and Pull Requests

Last synced: 7 months ago

All Time
  • Total issues: 5
  • Total pull requests: 2
  • Average time to close issues: 7 months
  • Average time to close pull requests: 2 days
  • Total issue authors: 5
  • Total pull request authors: 2
  • Average comments per issue: 2.2
  • Average comments per pull request: 0.0
  • Merged pull requests: 1
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • ArezooAalipanah (1)
  • catubc (1)
  • rosewang2008 (1)
  • siddhya (1)
  • kierad (1)
Pull Request Authors
  • herambnemlekar (1)
  • NiftyJ (1)
Top Labels
Issue Labels
Pull Request Labels

Packages

  • Total packages: 1
  • Total downloads:
    • pypi 2,054 last-month
  • Total dependent packages: 0
  • Total dependent repositories: 1
  • Total versions: 1
  • Total maintainers: 1
pypi.org: irl-maxent

A small package for Maximum Entropy Inverse Reinforcement Learning on simple MDPs

  • Versions: 1
  • Dependent Packages: 0
  • Dependent Repositories: 1
  • Downloads: 2,054 Last month
Rankings
Stargazers count: 5.7%
Forks count: 6.0%
Dependent packages count: 10.0%
Average: 17.2%
Dependent repos count: 21.8%
Downloads: 42.6%
Maintainers (1)
qzed
Last synced: 6 months ago

Dependencies

requirements.txt pypi
  • matplotlib >=3.1.0
  • numpy >=1.18.0
  • pytest >=5.3.0
setup.py pypi
  • matplotlib *
  • numpy *