{"id":13573606,"url":"https://github.com/ADGEfficiency/energy-py","last_synced_at":"2025-04-04T12:31:11.987Z","repository":{"id":39740275,"uuid":"87061522","full_name":"ADGEfficiency/energy-py","owner":"ADGEfficiency","description":"Reinforcement learning for energy systems","archived":false,"fork":false,"pushed_at":"2023-03-25T01:04:44.000Z","size":121,"stargazers_count":174,"open_issues_count":6,"forks_count":33,"subscribers_count":12,"default_branch":"main","last_synced_at":"2024-06-11T17:45:38.212Z","etag":null,"topics":["energy","reinforcement-learning"],"latest_commit_sha":null,"homepage":"","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/ADGEfficiency.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2017-04-03T10:14:01.000Z","updated_at":"2024-05-10T21:33:29.000Z","dependencies_parsed_at":"2023-09-21T19:48:03.771Z","dependency_job_id":null,"html_url":"https://github.com/ADGEfficiency/energy-py","commit_stats":{"total_commits":14,"total_committers":2,"mean_commits":7.0,"dds":0.2142857142857143,"last_synced_commit":"ac4b2dbcfb2e9d1200373213e2d3cdbe15780278"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ADGEfficiency%2Fenergy-py","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ADGEfficiency%2Fenergy-py/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ADGEfficiency%2Fenergy-py/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ADGEfficiency%2Fenergy-py/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ADGEfficiency","download_url":"https://codeload.github.com/ADGEfficiency/energy-py/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":233321120,"owners_count":18658343,"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":["energy","reinforcement-learning"],"created_at":"2024-08-01T15:00:38.164Z","updated_at":"2025-04-04T12:31:11.949Z","avatar_url":"https://github.com/ADGEfficiency.png","language":"Python","funding_links":[],"categories":["Energy and Physics","Energy Systems","Energy System Assessment"],"sub_categories":["Energy System Modeling Frameworks","Optimization"],"readme":"# energy-py\n\n[![Build Status](https://travis-ci.org/ADGEfficiency/energy-py.svg?branch=master)](https://travis-ci.org/ADGEfficiency/energy-py)\n\nenergy-py is a framework for running reinforcement learning experiments on energy environments.\n\nThe library is focused on electric battery storage, and offers a implementation of a many batteries operating in parallel.\n\nenergy-py includes an implementation of the Soft Actor-Critic reinforcement learning agent, implementated in Tensorflow 2:\n\n- test \u0026 train episodes based on historical Australian electricity price data,\n- checkpoints \u0026 restarts,\n- logging in Tensorboard.\n\nenergy-py is built and maintained by Adam Green - adam.green@adgefficiency.com.\n\n\n## Setup\n\n```bash\n$ make setup\n```\n\n\n## Test\n\n```bash\n$ make test\n```\n\n\n## Running experiments\n\n`energypy` has a high level API to run a specific run of an experiment from a `JSON` config file.\n\nThe most interesting experiment is to run battery storage for price arbitrage in the Australian electricity market.  This requires grabbing some data from S3.  The command below will download a pre-made dataset and unzip it to `./dataset`:\n\n```bash\n$ make pulls3-dataset\n```\n\nYou can then run the experiment from a JSON file:\n\n```bash\n$ energypy benchmarks/nem-battery.json\n```\n\nResults are saved into `./experiments/{env_name}/{run_name}`:\n\n```bash\n$ tree -L 3 experiments\nexperiments/\n└── battery\n    ├── nine\n    │   ├── checkpoints\n    │   ├── hyperparameters.json\n    │   ├── logs\n    │   └── tensorboard\n    └── random.pkl\n```\n\nAlso provide wrappers around two `gym` environments - Pendulum and Lunar Lander:\n\n```bash\n$ energypy benchmarks/pendulum.json\n```\n\nRunning the Lunar Lander experiment has a dependency on Swig and pybox2d - which can require a bit of elbow-grease to setup depending on your environment.\n\n```bash\n$ energypy benchmarks/lunar.json\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FADGEfficiency%2Fenergy-py","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FADGEfficiency%2Fenergy-py","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FADGEfficiency%2Fenergy-py/lists"}