{"id":13936143,"url":"https://github.com/openai/multiagent-competition","last_synced_at":"2025-04-13T07:49:20.800Z","repository":{"id":51567025,"uuid":"106572676","full_name":"openai/multiagent-competition","owner":"openai","description":" Code for the paper \"Emergent Complexity via Multi-agent Competition\"","archived":false,"fork":false,"pushed_at":"2023-04-02T11:57:48.000Z","size":17359,"stargazers_count":812,"open_issues_count":12,"forks_count":153,"subscribers_count":47,"default_branch":"master","last_synced_at":"2025-04-13T07:49:15.071Z","etag":null,"topics":["paper"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/1710.03748","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/openai.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}},"created_at":"2017-10-11T15:29:00.000Z","updated_at":"2025-04-13T02:30:19.000Z","dependencies_parsed_at":"2022-08-22T06:01:09.967Z","dependency_job_id":"2a50ea58-d117-408c-aeea-cb99ef2b7ed3","html_url":"https://github.com/openai/multiagent-competition","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/openai%2Fmultiagent-competition","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/openai%2Fmultiagent-competition/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/openai%2Fmultiagent-competition/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/openai%2Fmultiagent-competition/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/openai","download_url":"https://codeload.github.com/openai/multiagent-competition/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248681494,"owners_count":21144700,"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":["paper"],"created_at":"2024-08-07T23:02:25.005Z","updated_at":"2025-04-13T07:49:20.772Z","avatar_url":"https://github.com/openai.png","language":"Python","funding_links":[],"categories":["Python","Environment","Platforms"],"sub_categories":["Others","Gradient Ascent"],"readme":"**Status:** Archive (code is provided as-is, no updates expected)\n\n# Competitive Multi-Agent Environments\n\nThis repository contains the environments for the paper [Emergent Complexity via Multi-agent Competition](https://arxiv.org/abs/1710.03748)\n\n## Dependencies\nUse `pip install -r requirements.txt` to install dependencies. If you haven't used MuJoCo before, please refer to the [installation guide](https://github.com/openai/mujoco-py).\nThe code has been tested with the following dependencies:\n* Python version 3.6\n* [OpenAI GYM](https://github.com/openai/gym) version 0.9.1 with MuJoCo 1.31 support (use [mujoco-py version 0.5.7](https://github.com/openai/mujoco-py/tree/0.5))\n* [Tensorflow](https://www.tensorflow.org/versions/r1.1/install/) version 1.1.0\n* [Numpy](https://scipy.org/install.html) version 1.12.1\n\n## Installing Package\nAfter installing all dependencies, make sure gym works with support for MuJoCo environments.\nNext install `gym-compete` package as:\n```bash\ncd gym-compete\npip install -e .\n```\nCheck install is successful by coming out of the directory and trying `import gym_compete` in python console. Some users might require a `sudo pip install`.\n\n## Trying the environments\nAgent policies are provided for the various environments in folder `agent-zoo`. To see a demo of all the environments do:\n```bash\nbash demo_tasks.sh all\n```\nTo instead try a single environment use:\n```bash\nbash demo_tasks.sh \u003ctask\u003e\n```\nwhere `\u003ctask\u003e` is one of: `run-to-goal-humans`, `run-to-goal-ants`, `you-shall-not-pass`, `sumo-ants`, `sumo-humans` and `kick-and-defend`\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fopenai%2Fmultiagent-competition","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fopenai%2Fmultiagent-competition","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fopenai%2Fmultiagent-competition/lists"}