{"id":18055095,"url":"https://github.com/tung-nd/e2c-pytorch","last_synced_at":"2025-04-10T23:13:57.880Z","repository":{"id":82931114,"uuid":"208226651","full_name":"tung-nd/E2C-pytorch","owner":"tung-nd","description":"A pytorch implementation of the paper \"Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images\", NIPS, 2015","archived":false,"fork":false,"pushed_at":"2019-09-30T17:17:27.000Z","size":2117,"stargazers_count":14,"open_issues_count":1,"forks_count":2,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-10T23:13:50.538Z","etag":null,"topics":["python","pytorch","reinforcement-learning","representation-learning"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/tung-nd.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":"2019-09-13T08:40:14.000Z","updated_at":"2024-12-16T02:14:09.000Z","dependencies_parsed_at":null,"dependency_job_id":"28c47129-f223-4b2d-88d0-43eb3cdb5b74","html_url":"https://github.com/tung-nd/E2C-pytorch","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tung-nd%2FE2C-pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tung-nd%2FE2C-pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tung-nd%2FE2C-pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tung-nd%2FE2C-pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tung-nd","download_url":"https://codeload.github.com/tung-nd/E2C-pytorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248312135,"owners_count":21082638,"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":["python","pytorch","reinforcement-learning","representation-learning"],"created_at":"2024-10-31T00:13:43.084Z","updated_at":"2025-04-10T23:13:57.854Z","avatar_url":"https://github.com/tung-nd.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Embed to Control\n\nThis is a pytorch implementation of the paper \"[Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images](https://arxiv.org/abs/1506.07365)\", NIPS, 2015.\n\n**Note: This is not and official implementation.**\n\n### Installing\n\nFirst, clone the repository:\n\n```\ngit clone https://github.com/tungnd1705/E2C-pytorch.git\n```\n\nInstall the dependencies as listed in `env.yml` and activate the environment\n\n```\nconda env create -f env.yml\n\nconda activate e2c\n```\n\nThen install the patch version of gym in order to sample the pendulum data\n\n```\ncd gym\n\npython setup.py install\n```\n\n### Simulate training data\n\nCurrently the code supports simulating 3 environments: `planar`, `pendulum` and `cartpole`.\n\nIn order to generate data, simply run `python sample_{env_name}_data.py --sample_size={sample_size}`.\n\n**Note: the sample size is equal to the total number of training and test data**\n\nFor the planar task, we base on [this](https://github.com/ethanluoyc/e2c-pytorch) implementation and modify for our needs.\n\n### Training\n\nRun the ``train_e2c.py`` with your own settings. Example:\n\n```\npython train_e2c.py \\\n    --env=planar \\\n    --propor=3/4 \\\n    --batch_size=128 \\\n    --lr=0.0001 \\\n    --lam=0.25 \\\n    --num_iter=5000 \\\n    --iter_save=1000\n```\n\nYou can visualize the training process by running ``tensorboard --logdir=logs``.\n\n### Citation\n\nIf you find E2C useful in your research, please consider citing:\n\n```\n@inproceedings{watter2015embed,\n  title={Embed to control: A locally linear latent dynamics model for control from raw images},\n  author={Watter, Manuel and Springenberg, Jost and Boedecker, Joschka and Riedmiller, Martin},\n  booktitle={Advances in neural information processing systems},\n  pages={2746--2754},\n  year={2015}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftung-nd%2Fe2c-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftung-nd%2Fe2c-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftung-nd%2Fe2c-pytorch/lists"}