{"id":13528409,"url":"https://github.com/enlite-ai/maze","last_synced_at":"2026-01-14T07:56:34.374Z","repository":{"id":37315904,"uuid":"337969557","full_name":"enlite-ai/maze","owner":"enlite-ai","description":"Maze Applied Reinforcement Learning Framework","archived":false,"fork":false,"pushed_at":"2025-12-18T15:24:48.000Z","size":10762,"stargazers_count":285,"open_issues_count":2,"forks_count":12,"subscribers_count":6,"default_branch":"main","last_synced_at":"2025-12-20T04:43:20.355Z","etag":null,"topics":["applied-machine-learning","automation","data-science","decision-making","deep-learning","distributed","documentation","framework","machine-learning","monitoring","optimization","python","reinforcement-learning","simulation"],"latest_commit_sha":null,"homepage":"https://maze-rl.readthedocs.io/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/enlite-ai.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":".github/CONTRIBUTING.md","funding":null,"license":"LICENSE.txt","code_of_conduct":".github/CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":".github/SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2021-02-11T08:26:37.000Z","updated_at":"2025-12-07T06:19:04.000Z","dependencies_parsed_at":"2024-01-22T19:33:46.161Z","dependency_job_id":"f46e6b49-8b14-415d-b0d1-5ba11aaa1378","html_url":"https://github.com/enlite-ai/maze","commit_stats":{"total_commits":1044,"total_committers":4,"mean_commits":261.0,"dds":0.009578544061302652,"last_synced_commit":"94e9125020cd3cd87200c689128fcca4cf9c9569"},"previous_names":[],"tags_count":11,"template":false,"template_full_name":null,"purl":"pkg:github/enlite-ai/maze","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/enlite-ai%2Fmaze","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/enlite-ai%2Fmaze/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/enlite-ai%2Fmaze/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/enlite-ai%2Fmaze/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/enlite-ai","download_url":"https://codeload.github.com/enlite-ai/maze/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/enlite-ai%2Fmaze/sbom","scorecard":{"id":377593,"data":{"date":"2025-08-11","repo":{"name":"github.com/enlite-ai/maze","commit":"94e9125020cd3cd87200c689128fcca4cf9c9569"},"scorecard":{"version":"v5.2.1-40-gf6ed084d","commit":"f6ed084d17c9236477efd66e5b258b9d4cc7b389"},"score":4.6,"checks":[{"name":"Maintained","score":0,"reason":"0 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 0","details":null,"documentation":{"short":"Determines if the project is \"actively maintained\".","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#maintained"}},{"name":"Code-Review","score":0,"reason":"Found 0/1 approved changesets -- score normalized to 0","details":null,"documentation":{"short":"Determines if the project requires human code review before pull requests (aka merge requests) are merged.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#code-review"}},{"name":"Dangerous-Workflow","score":10,"reason":"no dangerous workflow patterns detected","details":null,"documentation":{"short":"Determines if the project's GitHub Action workflows avoid dangerous patterns.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#dangerous-workflow"}},{"name":"CII-Best-Practices","score":0,"reason":"no effort to earn an OpenSSF best practices badge detected","details":null,"documentation":{"short":"Determines if the project has an OpenSSF (formerly CII) Best Practices Badge.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#cii-best-practices"}},{"name":"Security-Policy","score":10,"reason":"security policy file detected","details":["Info: security policy file detected: .github/SECURITY.md:1","Info: Found linked content: .github/SECURITY.md:1","Info: Found disclosure, vulnerability, and/or timelines in security policy: .github/SECURITY.md:1","Info: Found text in security policy: .github/SECURITY.md:1"],"documentation":{"short":"Determines if the project has published a security policy.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#security-policy"}},{"name":"Token-Permissions","score":0,"reason":"detected GitHub workflow tokens with excessive permissions","details":["Warn: no topLevel permission defined: .github/workflows/codeql-analysis.yml:1","Warn: no topLevel permission defined: .github/workflows/github-ci.yml:1","Info: no jobLevel write permissions found"],"documentation":{"short":"Determines if the project's workflows follow the principle of least privilege.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#token-permissions"}},{"name":"Binary-Artifacts","score":10,"reason":"no binaries found in the repo","details":null,"documentation":{"short":"Determines if the project has generated executable (binary) artifacts in the source repository.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#binary-artifacts"}},{"name":"Vulnerabilities","score":10,"reason":"0 existing vulnerabilities detected","details":null,"documentation":{"short":"Determines if the project has open, known unfixed vulnerabilities.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#vulnerabilities"}},{"name":"License","score":9,"reason":"license file detected","details":["Info: project has a license file: LICENSE.txt:0","Warn: project license file does not contain an FSF or OSI license."],"documentation":{"short":"Determines if the project has defined a license.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#license"}},{"name":"Fuzzing","score":0,"reason":"project is not fuzzed","details":["Warn: no fuzzer integrations found"],"documentation":{"short":"Determines if the project uses fuzzing.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#fuzzing"}},{"name":"Signed-Releases","score":0,"reason":"Project has not signed or included provenance with any releases.","details":["Warn: release artifact v0.1.8 not signed: https://api.github.com/repos/enlite-ai/maze/releases/55057593","Warn: release artifact v0.1.8 does not have provenance: https://api.github.com/repos/enlite-ai/maze/releases/55057593"],"documentation":{"short":"Determines if the project cryptographically signs release artifacts.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#signed-releases"}},{"name":"Branch-Protection","score":3,"reason":"branch protection is not maximal on development and all release branches","details":["Info: 'allow deletion' disabled on branch 'main'","Info: 'allow deletion' disabled on branch 'dev'","Info: 'force pushes' disabled on branch 'main'","Info: 'force pushes' disabled on branch 'dev'","Warn: 'branch protection settings apply to administrators' is disabled on branch 'main'","Warn: 'branch protection settings apply to administrators' is disabled on branch 'dev'","Warn: could not determine whether codeowners review is allowed","Warn: could not determine whether codeowners review is allowed","Warn: no status checks found to merge onto branch 'main'","Warn: no status checks found to merge onto branch 'dev'","Warn: PRs are not required to make changes on branch 'main'; or we don't have data to detect it.If you think it might be the latter, make sure to run Scorecard with a PAT or use Repo Rules (that are always public) instead of Branch Protection settings","Warn: PRs are not required to make changes on branch 'dev'; or we don't have data to detect it.If you think it might be the latter, make sure to run Scorecard with a PAT or use Repo Rules (that are always public) instead of Branch Protection settings"],"documentation":{"short":"Determines if the default and release branches are protected with GitHub's branch protection settings.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#branch-protection"}},{"name":"Pinned-Dependencies","score":0,"reason":"dependency not pinned by hash detected -- score normalized to 0","details":["Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/codeql-analysis.yml:38: update your workflow using https://app.stepsecurity.io/secureworkflow/enlite-ai/maze/codeql-analysis.yml/main?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/codeql-analysis.yml:42: update your workflow using https://app.stepsecurity.io/secureworkflow/enlite-ai/maze/codeql-analysis.yml/main?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/codeql-analysis.yml:53: update your workflow using https://app.stepsecurity.io/secureworkflow/enlite-ai/maze/codeql-analysis.yml/main?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/codeql-analysis.yml:67: update your workflow using https://app.stepsecurity.io/secureworkflow/enlite-ai/maze/codeql-analysis.yml/main?enable=pin","Warn: third-party GitHubAction not pinned by hash: .github/workflows/github-ci.yml:171: update your workflow using https://app.stepsecurity.io/secureworkflow/enlite-ai/maze/github-ci.yml/main?enable=pin","Warn: third-party GitHubAction not pinned by hash: .github/workflows/github-ci.yml:174: update your workflow using https://app.stepsecurity.io/secureworkflow/enlite-ai/maze/github-ci.yml/main?enable=pin","Warn: third-party GitHubAction not pinned by hash: .github/workflows/github-ci.yml:181: update your workflow using https://app.stepsecurity.io/secureworkflow/enlite-ai/maze/github-ci.yml/main?enable=pin","Warn: third-party GitHubAction not pinned by hash: .github/workflows/github-ci.yml:22: update your workflow using https://app.stepsecurity.io/secureworkflow/enlite-ai/maze/github-ci.yml/main?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/github-ci.yml:27: update your workflow using https://app.stepsecurity.io/secureworkflow/enlite-ai/maze/github-ci.yml/main?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/github-ci.yml:34: update your workflow using https://app.stepsecurity.io/secureworkflow/enlite-ai/maze/github-ci.yml/main?enable=pin","Warn: third-party GitHubAction not pinned by hash: .github/workflows/github-ci.yml:41: update your workflow using https://app.stepsecurity.io/secureworkflow/enlite-ai/maze/github-ci.yml/main?enable=pin","Warn: third-party GitHubAction not pinned by hash: .github/workflows/github-ci.yml:47: update your workflow using https://app.stepsecurity.io/secureworkflow/enlite-ai/maze/github-ci.yml/main?enable=pin","Warn: third-party GitHubAction not pinned by hash: .github/workflows/github-ci.yml:56: update your workflow using https://app.stepsecurity.io/secureworkflow/enlite-ai/maze/github-ci.yml/main?enable=pin","Warn: third-party GitHubAction not pinned by hash: .github/workflows/github-ci.yml:109: update your workflow using https://app.stepsecurity.io/secureworkflow/enlite-ai/maze/github-ci.yml/main?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/github-ci.yml:114: update your workflow using https://app.stepsecurity.io/secureworkflow/enlite-ai/maze/github-ci.yml/main?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/github-ci.yml:121: update your workflow using https://app.stepsecurity.io/secureworkflow/enlite-ai/maze/github-ci.yml/main?enable=pin","Warn: third-party GitHubAction not pinned by hash: .github/workflows/github-ci.yml:128: update your workflow using https://app.stepsecurity.io/secureworkflow/enlite-ai/maze/github-ci.yml/main?enable=pin","Warn: third-party GitHubAction not pinned by hash: .github/workflows/github-ci.yml:134: update your workflow using https://app.stepsecurity.io/secureworkflow/enlite-ai/maze/github-ci.yml/main?enable=pin","Warn: third-party GitHubAction not pinned by hash: .github/workflows/github-ci.yml:143: update your workflow using https://app.stepsecurity.io/secureworkflow/enlite-ai/maze/github-ci.yml/main?enable=pin","Warn: containerImage not pinned by hash: docker/maze-core-env.dockerfile:12","Warn: containerImage not pinned by hash: docker/maze-core-env.dockerfile:39","Warn: containerImage not pinned by hash: docker/maze-core.dockerfile:6","Warn: containerImage not pinned by hash: docker/playground.dockerfile:4: pin your Docker image by updating enliteai/maze:latest to enliteai/maze:latest@sha256:e918af87cee48f6e0a8251cbbac15e8ae1084ddf52658ed04ee6329e4ce0a345","Warn: pipCommand not pinned by hash: docker/maze-core-env.dockerfile:28","Warn: pipCommand not pinned by hash: docker/maze-core.dockerfile:9","Warn: pipCommand not pinned by hash: docker/playground.dockerfile:6","Info:   0 out of   8 GitHub-owned GitHubAction dependencies pinned","Info:   0 out of  11 third-party GitHubAction dependencies pinned","Info:   0 out of   4 containerImage dependencies pinned","Info:   0 out of   3 pipCommand dependencies pinned"],"documentation":{"short":"Determines if the project has declared and pinned the dependencies of its build process.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#pinned-dependencies"}},{"name":"Packaging","score":10,"reason":"packaging workflow detected","details":["Info: Project packages its releases by way of GitHub Actions.: .github/workflows/github-ci.yml:8"],"documentation":{"short":"Determines if the project is published as a package that others can easily download, install, easily update, and uninstall.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#packaging"}},{"name":"SAST","score":7,"reason":"SAST tool detected but not run on all commits","details":["Info: SAST configuration detected: CodeQL","Warn: 0 commits out of 30 are checked with a SAST tool"],"documentation":{"short":"Determines if the project uses static code analysis.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#sast"}}]},"last_synced_at":"2025-08-18T14:38:20.062Z","repository_id":37315904,"created_at":"2025-08-18T14:38:20.062Z","updated_at":"2025-08-18T14:38:20.062Z"},"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28413527,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-14T05:26:33.345Z","status":"ssl_error","status_checked_at":"2026-01-14T05:21:57.251Z","response_time":107,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["applied-machine-learning","automation","data-science","decision-making","deep-learning","distributed","documentation","framework","machine-learning","monitoring","optimization","python","reinforcement-learning","simulation"],"created_at":"2024-08-01T07:00:18.687Z","updated_at":"2026-01-14T07:56:34.369Z","avatar_url":"https://github.com/enlite-ai.png","language":"Python","funding_links":[],"categories":["Libraries","Python","Researchers"],"sub_categories":["General-Purpose Machine Learning","Frameworks"],"readme":"![Banner](https://github.com/enlite-ai/maze/raw/main/docs/source/_static/logos/logo-mazerl-light-mode-wbg.png)  \n[![CodeQL](https://github.com/enlite-ai/maze/actions/workflows/codeql-analysis.yml/badge.svg)](https://github.com/enlite-ai/maze/actions/workflows/codeql-analysis.yml)\n![PyPI](https://img.shields.io/pypi/v/maze-rl)\n![PyPI - Python Version](https://img.shields.io/pypi/pyversions/maze-rl)\n[![Maze Docker Image](https://github.com/enlite-ai/maze/actions/workflows/github-ci.yml/badge.svg)](https://github.com/enlite-ai/maze/actions/workflows/github-ci.yml)\n![Read the Docs](https://img.shields.io/readthedocs/maze-rl)\n[![contributions welcome](https://img.shields.io/badge/contributions-welcome-brightgreen.svg?style=flat)](https://github.com/enlite-ai/maze/issues)\n\n# Applied Reinforcement Learning with Python\n\nMazeRL is an application oriented Deep Reinforcement Learning (RL) framework, addressing real-world decision problems.\nOur vision is to cover the complete development life cycle of RL applications ranging from simulation \nengineering up to agent development, training and deployment.\n\n*This is a preliminary, non-stable release of Maze. It is not yet complete and not all of our interfaces have settled\nyet. Hence, there might be some breaking changes on our way towards the first stable release.*\n\n## Spotlight Features\n\nBelow we list a few selected Maze features.\n\n - Design and visualize your policy and value networks with the \n   [Perception Module](https://maze-rl.readthedocs.io/en/latest/policy_and_value_networks/perception_overview.html). \n   It is based on PyTorch and provides a large variety of neural network building blocks and model styles. \n   Quickly compose powerful representation learners from building blocks such as: dense, \n   convolution, graph convolution and attention, recurrent architectures, action- and observation masking, \n   self-attention etc.\n - Create the conditions for efficient RL training without writing boiler plate code, e.g. by supporting \n   best practices like [pre-processing](https://maze-rl.readthedocs.io/en/latest/environment_customization/observation_pre_processing.html) and \n   [normalizing](https://maze-rl.readthedocs.io/en/latest/environment_customization/observation_normalization.html) your observations.\n - Maze supports advanced [environment structures](https://maze-rl.readthedocs.io/en/latest/concepts_and_structure/env_hierarchy.html) reflecting \n   the requirements of real-world industrial decision problems such as multi-step and multi-agent scenarios. \n   You can of course work with existing [Gym-compatible environments](https://maze-rl.readthedocs.io/en/latest/best_practices_and_tutorials/integrating_gym_environment.html).\n - Use the provided [Maze trainers](https://maze-rl.readthedocs.io/en/latest/trainers/maze_trainers.html) (A2C, PPO, Impala, SAC, Evolution Strategies), \n   which are supporting dictionary action and observation spaces as well as multi-step (auto-regressive policies) training. \n - Out of the box support for advanced training workflows such as [imitation learning from teacher policies and \n   policy fine-tuning](https://maze-rl.readthedocs.io/en/latest/workflow/imitation_and_fine_tuning.html). \n - Keep even complex application and experiment configuration manageable with the [Hydra Config System](https://maze-rl.readthedocs.io/en/latest/concepts_and_structure/hydra.html).\n \n## Get Started\n\n* Make sure [PyTorch](https://pytorch.org/get-started/locally/) is installed and then get the latest released version of Maze as follows:\n\n      pip install -U maze-rl\n      \n  [Read more about other options](https://maze-rl.readthedocs.io/en/latest/getting_started/installation.html) like the installation of the latest \n  development version.  \n\n  :zap: Maze is compatible with Python 3.9 to 3.10. We encourage you to start with **Python 3.10**. \n  If you intend to use popular environments like Atari or Box2D you might need to [install additional binary dependencies manually](https://maze-rl.readthedocs.io/en/latest/getting_started/installation.html).\n* Alternatively you can work with Maze in a \u003cimg alt=\"Docker\" src=\"https://upload.wikimedia.org/wikipedia/commons/thumb/4/4e/Docker_%28container_engine%29_logo.svg/1280px-Docker_%28container_engine%29_logo.svg.png\" width=\"100\" height=\"22\" /\u003e container with pre-installed Jupyter lab: Run `docker run -p 8888:8888 enliteai/maze:playground` and open `localhost:8888` in your browser.\n* To see Maze in action, check out a [first example](https://maze-rl.readthedocs.io/en/latest/getting_started/first_example.html).\n* [Try your own Gym env](https://maze-rl.readthedocs.io/en/latest/best_practices_and_tutorials/integrating_gym_environment.html)\n  or visit our [Maze step-by-step tutorial](https://maze-rl.readthedocs.io/en/latest/getting_started/step_by_step_tutorial.html).\n\n\u003ctable\u003e\u003ctbody\u003e\u003ctr\u003e\n    \u003ctd align=\"center\"\u003e\u003ca href=\"https://maze-rl.readthedocs.io/en/latest/getting_started/installation.html\"\u003e\n        \u003cimg src=\"https://github.com/enlite-ai/maze/raw/main/.github/pip.png\" alt=\"Pip\" width=\"128px\"\u003e\u003cbr\u003e\n        \u003cstrong\u003eInstallation\u003c/strong\u003e\n    \u003c/a\u003e\u003c/td\u003e\n    \u003ctd align=\"center\"\u003e\u003ca href=\"https://maze-rl.readthedocs.io/en/latest/getting_started/first_example.html\"\u003e\n        \u003cimg src=\"https://github.com/enlite-ai/maze/raw/main/.github/start.png\" alt=\"First Example\" width=\"128px\"\u003e\u003cbr\u003e\n        \u003cstrong\u003eFirst Example\u003c/strong\u003e\n    \u003c/a\u003e\u003c/td\u003e\n    \u003ctd align=\"center\"\u003e\u003ca href=\"https://maze-rl.readthedocs.io/en/latest/getting_started/step_by_step_tutorial.html\"\u003e\n        \u003cimg src=\"https://github.com/enlite-ai/maze/raw/main/.github/steps.png\" alt=\"Tutorial\" width=\"128px\"\u003e\u003cbr\u003e\n        \u003cstrong\u003eStep by Step Tutorial\u003c/strong\u003e\n    \u003c/a\u003e\u003c/td\u003e\n    \u003ctd align=\"center\"\u003e\u003ca href=\"https://maze-rl.readthedocs.io/en/latest/\"\u003e\n        \u003cimg src=\"https://github.com/enlite-ai/maze/raw/main/.github/paper.png\" alt=\"Documentation\" width=\"128px\"\u003e\u003cbr\u003e\n        \u003cstrong\u003eDocumentation\u003c/strong\u003e\n    \u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\u003c/tbody\u003e\u003c/table\u003e\n\n* Clone this [project template repo](https://github.com/enlite-ai/maze-cartpole) to start your own Maze project.\n\n## Learn more about Maze\n\nThe [documentation](https://maze-rl.readthedocs.io/en/latest/index.html#documentation-overview) is the starting point to learn more about\n  the underlying concepts, but most importantly, also provides code snippets and minimum working examples to \n  get you started quickly.\n\n* The *Workflow* section guides you through typical tasks in a RL project\n  * [Training](https://maze-rl.readthedocs.io/en/latest/workflow/training.html)\n  * [Rollouts](https://maze-rl.readthedocs.io/en/latest/workflow/rollouts.html)\n  * [Collection and Visualizing Rollouts](https://maze-rl.readthedocs.io/en/latest/workflow/rollouts_trajectories_viewer.html)\n  * [Imitation Learning and Fine-Tuning](https://maze-rl.readthedocs.io/en/latest/workflow/imitation_and_fine_tuning.html) \n\n* *Policy and Value Networks* introduces you to the \n  [Perception Module](https://maze-rl.readthedocs.io/en/latest/policy_and_value_networks/perception_overview.html), \n  how to [customize action spaces and the underlying action probability distributions](https://maze-rl.readthedocs.io/en/latest/policy_and_value_networks/distributions_and_action_heads.html) \n  and two styles of policy and value networks construction:\n  \n  * [Template models](https://maze-rl.readthedocs.io/en/latest/policy_and_value_networks/perception_template_models.html) \n    are composed directly from an environment's observation and action space,\n    allowing you to train with suitable agent networks on a new environment within minutes.\n    \n  * [Custom models](https://maze-rl.readthedocs.io/en/latest/policy_and_value_networks/perception_custom_models.html) gives you the full \n    flexibility of application specific models, either with the provided Maze building blocks or \n    directly with PyTorch. \n\n* Learn more about core *concepts and structures* such as the \n  [Maze environment hierarchy](https://maze-rl.readthedocs.io/en/latest/concepts_and_structure/env_hierarchy.html), the \n  [Maze event system](https://maze-rl.readthedocs.io/en/latest/concepts_and_structure/event_system.html) providing a convenient way to collect \n  statistics and KPIs, enable flexible reward formulation and supporting offline analysis. \n\n* [Structured Environments and Action Masking](https://maze-rl.readthedocs.io/en/latest/best_practices_and_tutorials/struct_env_tutorial.html) \n  introduces you to a general concept, which can greatly improve\n  the performance of the trained agents in practical RL problems.\n\n## License\n\nMaze is freely available for research and non-commercial use. A commercial license is available, if interested please \ncontact us on our [company website](https://enlite.ai) or write us an [email](mailto:office@enlite.ai).\n\nWe believe in Open Source principles and aim at transitioning Maze to a commercial Open Source project, \nreleasing larger parts of the framework under a permissive license in the near future.  \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fenlite-ai%2Fmaze","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fenlite-ai%2Fmaze","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fenlite-ai%2Fmaze/lists"}