{"id":17838477,"url":"https://github.com/haoliuhl/taming-maml","last_synced_at":"2025-03-19T23:30:54.727Z","repository":{"id":112163004,"uuid":"184635343","full_name":"haoliuhl/taming-maml","owner":"haoliuhl","description":"Taming MAML: efficient unbiased meta-reinforcement learning","archived":false,"fork":false,"pushed_at":"2022-09-30T19:47:10.000Z","size":199,"stargazers_count":29,"open_issues_count":3,"forks_count":3,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-02-28T21:37:02.762Z","etag":null,"topics":["meta-learning","reinfor"],"latest_commit_sha":null,"homepage":null,"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/haoliuhl.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,"publiccode":null,"codemeta":null}},"created_at":"2019-05-02T18:56:11.000Z","updated_at":"2024-10-11T10:43:28.000Z","dependencies_parsed_at":"2023-03-26T14:50:43.896Z","dependency_job_id":null,"html_url":"https://github.com/haoliuhl/taming-maml","commit_stats":null,"previous_names":["forhaoliu/taming-maml","haoliuhl/taming-maml"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/haoliuhl%2Ftaming-maml","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/haoliuhl%2Ftaming-maml/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/haoliuhl%2Ftaming-maml/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/haoliuhl%2Ftaming-maml/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/haoliuhl","download_url":"https://codeload.github.com/haoliuhl/taming-maml/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244030781,"owners_count":20386532,"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":["meta-learning","reinfor"],"created_at":"2024-10-27T20:57:04.754Z","updated_at":"2025-03-19T23:30:54.722Z","avatar_url":"https://github.com/haoliuhl.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Taming MAML: Efficient unbiased meta-reinforcement learning\n\nReference Tensorflow implementation of [Taming MAML: Efficient unbiased meta-reinforcement learning](http://proceedings.mlr.press/v97/liu19g.html).\nWe will release Pytorch version later.\n\n\n## Getting started\nYou can use [Dockerfile](Dockerfile) to build an image with conda environment called _tmaml_ included, activating this conda env:\n```\nconda activate tmaml\n```\nyou can also use [`tmaml.yml`](tmaml.yml) to create a conda env called _tmaml_.\n```\nconda env create -f tmaml.yml\n```\nthen activate this conda env\n```\nconda activate tmaml\n```\n\n## Usage\nYou can use the [`tmaml_run_mujoco.py`](tmaml_run_mujoco.py) , [`vpg_run_mujoco.py`](vpg_run_mujoco.py) and [`dice_vpg_run_mujoco.py`](dice_vpg_run_mujoco.py) scripts in order to run reinforcement learning experiments with different algorithm.\nMAML:\n```\npython vpg_run_mujoco.py --env HalfCheetahRandDirecEnv\n```\nMAML + DICE:\n```\npython dice_vpg_run_mujoco.py --env HalfCheetahRandDirecEnv\n```\nTMAML:\n```\npython tmaml_run_mujoco.py --env HalfCheetahRandDirecEnv\n```\n\n\n### References\nTo cite TMAML please use\n```\n@InProceedings{pmlr-v97-liu19g,\n  title = \t {Taming {MAML}: Efficient unbiased meta-reinforcement learning},\n  author = \t {Liu, Hao and Socher, Richard and Xiong, Caiming},\n  booktitle = \t {Proceedings of the 36th International Conference on Machine Learning},\n  pages = \t {4061--4071},\n  year = \t {2019},\n  editor = \t {Chaudhuri, Kamalika and Salakhutdinov, Ruslan},\n  volume = \t {97},\n  series = \t {Proceedings of Machine Learning Research},\n  address = \t {Long Beach, California, USA},\n  month = \t {09--15 Jun},\n  publisher = \t {PMLR},\n}\n```\n\n#### TODOs\n- [x] Adding TMAML\n- [x] Adding MAML\n- [x] Adding DICE\n- [ ] Benchmarking\n- [ ] Pytorch version\n\n### Acknowledgements\nThis repository is based on [ProMP repo](https://github.com/jonasrothfuss/ProMP).","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhaoliuhl%2Ftaming-maml","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhaoliuhl%2Ftaming-maml","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhaoliuhl%2Ftaming-maml/lists"}