{"id":20131287,"url":"https://github.com/qzed/irl-maxent","last_synced_at":"2025-04-05T06:02:51.889Z","repository":{"id":42121617,"uuid":"185288428","full_name":"qzed/irl-maxent","owner":"qzed","description":"Maximum Entropy and Maximum Causal Entropy Inverse Reinforcement Learning Implementation in Python","archived":false,"fork":false,"pushed_at":"2024-04-21T12:57:08.000Z","size":1410,"stargazers_count":272,"open_issues_count":3,"forks_count":61,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-03-29T05:09:22.773Z","etag":null,"topics":["inverse-reinforcement-learning","machine-learning","maximum-entropy"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/qzed.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-05-06T23:57:32.000Z","updated_at":"2025-03-25T14:48:54.000Z","dependencies_parsed_at":"2022-09-09T13:12:01.806Z","dependency_job_id":"9d890bd1-9bdd-45a6-8a9b-fa912135aa8e","html_url":"https://github.com/qzed/irl-maxent","commit_stats":{"total_commits":106,"total_committers":3,"mean_commits":"35.333333333333336","dds":0.1132075471698113,"last_synced_commit":"549c3e3de05401ad303600d83cf78fc5d416803f"},"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/qzed%2Firl-maxent","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/qzed%2Firl-maxent/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/qzed%2Firl-maxent/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/qzed%2Firl-maxent/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/qzed","download_url":"https://codeload.github.com/qzed/irl-maxent/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247294514,"owners_count":20915340,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["inverse-reinforcement-learning","machine-learning","maximum-entropy"],"created_at":"2024-11-13T20:47:24.965Z","updated_at":"2025-04-05T06:02:51.859Z","avatar_url":"https://github.com/qzed.png","language":"Jupyter Notebook","funding_links":[],"categories":["🚀 GitHub Repositories"],"sub_categories":["🌟 **Real-World Magic**"],"readme":"# Maximum Entropy Inverse Reinforcement Learning\n\nThis 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.\nProject for the Advanced Seminar in Imitation Learning, summer term 2019, University of Stuttgart.\n\nThis implementation is available as python package at https://pypi.org/project/irl-maxent/ and can be installed via `pip install irl-maxent`.\nYou may also want to have a look at the accompanying [presentation][presentation].\n\nFor an example demonstrating how the Maximum (non-causal) Entropy IRL algorithm works, see the corresponding Jupyter notebook ([`notebooks/maxent.ipynb`][nb-viewer]).\nNote that the provided python files (`src/`) contain a slightly more optimized implementation of the algorithms.\n\nTo run a demonstration without the notebook, you can directly run `./src/example.py`.\nAlso have a look at this file on how to use the provided framework.\nThe framework contains:\n- Two GridWorld implementations for demonstration (`irl_maxent.gridworld`)\n- The algorithm implementations (`irl_maxent.maxent`)\n- A gradient based optimizer framework (`irl_maxent.optimizer`)\n- Plotting helper functions (`irl_maxent.plot`)\n- A MDP solver framework, i.e. value iteration and corresponding utilities (`irl_maxent.solver`)\n- A trajectory/trajectory generation framework (`irl_maxent.trajectory`)\n\nThis project solely relies on the following dependencies: `numpy`, `matplotlib`, `itertools`, and `pytest`.\n\n[nb-viewer]: https://nbviewer.jupyter.org/github/qzed/irl-maxent/blob/master/notebooks/maxent.ipynb\n[presentation]: https://nbviewer.jupyter.org/github/qzed/irl-maxent/blob/master/Presentation.pdf\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fqzed%2Firl-maxent","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fqzed%2Firl-maxent","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fqzed%2Firl-maxent/lists"}