{"id":18858964,"url":"https://github.com/kohlerhector/tree-mbpo","last_synced_at":"2026-05-05T20:39:34.320Z","repository":{"id":220682276,"uuid":"752281271","full_name":"KohlerHECTOR/Tree-MBPO","owner":"KohlerHECTOR","description":"Study Model-Based Policy Optimization by varying the model estimator classes (e.g Decision Trees vs MLP)","archived":false,"fork":false,"pushed_at":"2024-02-07T10:40:46.000Z","size":3245,"stargazers_count":3,"open_issues_count":3,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-12-30T19:49:23.165Z","etag":null,"topics":["decision-tree","mbpo","mbrl","mlp","rl","sac","scikit-learn","stable-baselines3"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/KohlerHECTOR.png","metadata":{"files":{"readme":"readme.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null}},"created_at":"2024-02-03T15:09:41.000Z","updated_at":"2024-04-24T03:40:51.000Z","dependencies_parsed_at":"2024-02-07T11:52:51.988Z","dependency_job_id":"e48abfbf-ba00-44ff-bf09-559efdc63599","html_url":"https://github.com/KohlerHECTOR/Tree-MBPO","commit_stats":null,"previous_names":["kohlerhector/mbdtrl","kohlerhector/mbpo-scikit-stable","kohlerhector/tree-mbpo"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KohlerHECTOR%2FTree-MBPO","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KohlerHECTOR%2FTree-MBPO/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KohlerHECTOR%2FTree-MBPO/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KohlerHECTOR%2FTree-MBPO/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/KohlerHECTOR","download_url":"https://codeload.github.com/KohlerHECTOR/Tree-MBPO/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239800427,"owners_count":19699122,"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":["decision-tree","mbpo","mbrl","mlp","rl","sac","scikit-learn","stable-baselines3"],"created_at":"2024-11-08T04:15:18.416Z","updated_at":"2026-02-07T21:30:17.878Z","avatar_url":"https://github.com/KohlerHECTOR.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"###### For Tree-Based-Exploration see: https://github.com/KohlerHECTOR/TREX-Tree-Reward-EXploration\n## Only Continuous actions\n\n\nInstall scikit-learn and SB3\n\n```pip3 install -r requirements.txt```\n\n![trees-mlp](https://github.com/KohlerHECTOR/MBPO-Scikit-Stable/blob/main/mbpo_schematics_rdme/evals.png?raw=true)\n\n![trees-mlp-times](https://github.com/KohlerHECTOR/MBPO-Scikit-Stable/blob/main/mbpo_schematics_rdme/times.png?raw=true)\n\n![trees](https://github.com/KohlerHECTOR/MBPO-Scikit-Stable/blob/main/mbpo_schematics_rdme/evals-gsteps.png?raw=true)\n\n\n### Available Models are Decision Trees, best CV Trees, and MLPs\n### Available Policy Optim Algos are SAC and TD3\n\nLaunch MBPO for 100 iterations on InvertedPendulum with Decision Trees as Model estimators and SAC as policy optim.\nResults are saved in 'Experience_Results/pendul-tree-sac/':\n\n```python3 experience.py InvertedPendulum-v4 tree sac 100 pendul-tree-sac```\n\nLaunch MBPO for 100 iterations on InvertedPendulum with 2x64 MLP as Model estimators and SAC as policy optim.\nResults are saved in 'Experience_Results/pendul-mlp-sac/':\n\n```python3 experience.py InvertedPendulum-v4 mlp sac 100 pendul-mlp-sac```\n\nSave Plots of comparisons 'Experience_Results/Comparison-date-time/':\n\n```python3 compare_experiences.py pendul-tree-sac pendul-mlp-sac```\n\nSave Plots of results in 'Experience_Results/pendul-tree-sac/':\n\n```python3 plot_experience.py pendul-tree-sac```\n\nMBPO: https://arxiv.org/abs/1906.08253\n\n![MBPO-structure](https://github.com/KohlerHECTOR/MBPO-Scikit-Stable/blob/main/mbpo_schematics_rdme/mbpo-structure.png?raw=true)\n![MBPO-rollout](https://github.com/KohlerHECTOR/MBPO-Scikit-Stable/blob/main/mbpo_schematics_rdme/mbpo-rollout.png?raw=true)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkohlerhector%2Ftree-mbpo","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkohlerhector%2Ftree-mbpo","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkohlerhector%2Ftree-mbpo/lists"}