{"id":18767418,"url":"https://github.com/miffyli/minecraft-bc","last_synced_at":"2025-04-13T06:32:22.680Z","repository":{"id":56335008,"uuid":"259333499","full_name":"Miffyli/minecraft-bc","owner":"Miffyli","description":"Submission code of UEFDRL team to NeurIPS 2019 MineRL challenge (5th place)","archived":false,"fork":false,"pushed_at":"2020-11-13T17:46:09.000Z","size":22,"stargazers_count":13,"open_issues_count":0,"forks_count":2,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-03-26T23:21:07.913Z","etag":null,"topics":["imitation-learning","keras","machine-learning","minecraft"],"latest_commit_sha":null,"homepage":null,"language":"Python","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/Miffyli.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-04-27T13:38:36.000Z","updated_at":"2024-12-02T21:57:39.000Z","dependencies_parsed_at":"2022-08-15T16:50:35.995Z","dependency_job_id":null,"html_url":"https://github.com/Miffyli/minecraft-bc","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/Miffyli%2Fminecraft-bc","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Miffyli%2Fminecraft-bc/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Miffyli%2Fminecraft-bc/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Miffyli%2Fminecraft-bc/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Miffyli","download_url":"https://codeload.github.com/Miffyli/minecraft-bc/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248674678,"owners_count":21143760,"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":["imitation-learning","keras","machine-learning","minecraft"],"created_at":"2024-11-07T19:07:23.630Z","updated_at":"2025-04-13T06:32:22.325Z","avatar_url":"https://github.com/Miffyli.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Playing Minecraft with behavioural cloning\nThis repository contains the final ranked submission of UEFDRL team to the [MineRL 2019 challenge](https://www.aicrowd.com/challenges/neurips-2019-minerl-competition),\nreaching fifth place.\n\nLong story short: Behavioural cloning on the provided dataset, _i.e._ predict what actions humans would take. No RNNs.\n\nSee this paper for full details: [Playing Minecraft with Behavioural Cloning](https://arxiv.org/abs/2005.03374).\n\n## Contents\n\nCode is in the submission format, and can be ran with the instructions at [submission template repository](https://github.com/minerllabs/competition_submission_starter_template).\n`requirements.txt` contains Python modules required to run the code, and `apt.txt` includes any Debian packages required (used by the Docker image in AICrowd evaluation server).\n\nThe core of our submission resides in `train_keras_imitation.py`, which contains the main training loop. \n\n## Running\n\n[Download](http://minerl.io/dataset/) and place MineRL dataset under `./data`. Alternatively point environment variable `MINERL_DATA_ROOT` to the downloaded dataset.\n\nRun `train.py` to train the model. Afterwards run `test.py` to run the evaluation used in the AICrowd platform. This code prints out per-episode rewards.\n\nAfter 200 games, the average episodic reward should be around 10-13. The results very from run-to-run, and we also\nnoticed our local evaluations having consistently lower score than on AICrowd platform (achieved +15 results).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmiffyli%2Fminecraft-bc","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmiffyli%2Fminecraft-bc","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmiffyli%2Fminecraft-bc/lists"}