{"id":13936655,"url":"https://github.com/hi-abhi/tensorflow-value-iteration-networks","last_synced_at":"2025-07-19T22:31:24.330Z","repository":{"id":38325611,"uuid":"77414927","full_name":"hi-abhi/tensorflow-value-iteration-networks","owner":"hi-abhi","description":"TensorFlow implementation of the Value Iteration Networks (NIPS '16) paper","archived":false,"fork":false,"pushed_at":"2019-03-07T08:59:42.000Z","size":460,"stargazers_count":552,"open_issues_count":1,"forks_count":121,"subscribers_count":29,"default_branch":"master","last_synced_at":"2024-11-08T07:03:29.968Z","etag":null,"topics":["deep-learning","machine-learning","neural-networks","reinforcement-learning","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":false,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/hi-abhi.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2016-12-27T00:54:58.000Z","updated_at":"2024-07-27T03:23:46.000Z","dependencies_parsed_at":"2022-08-25T03:01:35.608Z","dependency_job_id":null,"html_url":"https://github.com/hi-abhi/tensorflow-value-iteration-networks","commit_stats":null,"previous_names":["hi-abhi/tensorflow-value-iteration-networks","theabhikumar/tensorflow-value-iteration-networks"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hi-abhi%2Ftensorflow-value-iteration-networks","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hi-abhi%2Ftensorflow-value-iteration-networks/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hi-abhi%2Ftensorflow-value-iteration-networks/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hi-abhi%2Ftensorflow-value-iteration-networks/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hi-abhi","download_url":"https://codeload.github.com/hi-abhi/tensorflow-value-iteration-networks/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":226686729,"owners_count":17666928,"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":["deep-learning","machine-learning","neural-networks","reinforcement-learning","tensorflow"],"created_at":"2024-08-07T23:02:53.411Z","updated_at":"2024-11-27T04:31:17.983Z","avatar_url":"https://github.com/hi-abhi.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# [Value Iteration Networks](https://arxiv.org/abs/1602.02867) in TensorFlow\n\n\u003e Tamar, A., Wu, Y., Thomas, G., Levine, S., and Abbeel, P. _Value Iteration Networks_. Neural Information Processing Systems (NIPS) 2016\n\nThis repository contains an implementation of Value Iteration Networks in TensorFlow which won the Best Paper Award at NIPS 2016. This code is based on the original Theano implementation by the authors.\n\n![Value Iteration Network and Module](assets/vin.png)\n\n## Training\n\n- Download the 16x16 and 28x28 GridWorld datasets from the [author's repository](https://github.com/avivt/VIN/tree/master/data). This repository contains the 8x8 GridWorld dataset for convenience and its small size.\n\n```\n# Runs the 8x8 Gridworld with default parameters\npython3 train.py\n```\n\nIf you want to monitor training progress change `config.log` to `True` and launch `tensorboard --logdir /tmp/vintf/`. The log directory is `/tmp/vintf/` by default, but can be changed in `config.logdir`. The code currently runs the 8x8 GridWorld model by default.\n\nThe 8x8 GridWorld model converges in under 30 epochs with about ~98.5% accuracy. The paper lists that it should be around 99.6% and I was able to reproduce this with the Theano code. Results for 16x16 and 28x28 can be seen [here](https://github.com/TheAbhiKumar/tensorflow-value-iteration-networks/issues/6)\n\n## Dependencies\n* Python \u003e= 3.6\n* TensorFlow \u003e= 1.0\n* SciPy \u003e= 0.18.1 (to load the data)\n\n## Datasets\n* The GridWorld dataset used is from the author's repository. It also contains Matlab scripts to generate the dataset. The code to process the dataset is from the original repository with minor modifications under this [license](https://github.com/avivt/VIN/blob/master/LICENSE.md)\n* The model was also originally tested on three other domains and the author's original code will be [released eventually](https://github.com/avivt/VIN/issues/4)\n  * Mars Rover Navigation\n  * Continuous control\n  * WebNav\n\n## Resources\n\n* [Value Iteration Networks on arXiv](https://arxiv.org/abs/1602.02867)\n* [Aviv Tamar's (author) original implementation in Theano](https://github.com/avivt/VIN)\n* [ICML Slides](http://docs.wixstatic.com/ugd/3195dc_6ab5cea3189741a3b605fc6fc1d79bb8.pdf)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhi-abhi%2Ftensorflow-value-iteration-networks","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhi-abhi%2Ftensorflow-value-iteration-networks","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhi-abhi%2Ftensorflow-value-iteration-networks/lists"}