{"id":24483152,"url":"https://github.com/sukiboo/policy_entropy","last_synced_at":"2026-05-15T13:35:33.241Z","repository":{"id":128451895,"uuid":"523398876","full_name":"sukiboo/policy_entropy","owner":"sukiboo","description":"Analyzing policy entropy of reinforcement learning agents","archived":false,"fork":false,"pushed_at":"2023-08-18T12:19:37.000Z","size":22572,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-08-20T07:28:49.378Z","etag":null,"topics":["mathematics","policy-gradient","q-learning","reinforcement-learning","stable-baselines3"],"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/sukiboo.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-08-10T15:32:16.000Z","updated_at":"2023-09-11T12:38:57.000Z","dependencies_parsed_at":null,"dependency_job_id":"14754fa4-acc4-4f47-81d6-1f9d194b412c","html_url":"https://github.com/sukiboo/policy_entropy","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/sukiboo/policy_entropy","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sukiboo%2Fpolicy_entropy","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sukiboo%2Fpolicy_entropy/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sukiboo%2Fpolicy_entropy/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sukiboo%2Fpolicy_entropy/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sukiboo","download_url":"https://codeload.github.com/sukiboo/policy_entropy/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sukiboo%2Fpolicy_entropy/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33068710,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-15T11:35:32.926Z","status":"ssl_error","status_checked_at":"2026-05-15T11:35:31.362Z","response_time":103,"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":["mathematics","policy-gradient","q-learning","reinforcement-learning","stable-baselines3"],"created_at":"2025-01-21T12:31:05.282Z","updated_at":"2026-05-15T13:35:33.224Z","avatar_url":"https://github.com/sukiboo.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Policy Entropy of RL Agents\n\nThis repository contains the source code for the numerical experiments presented in the paper \"[Analyzing Policy Entropy of Reinforcement Learning Agents for Personalization Tasks](https://arxiv.org/abs/2211.11869)\".\n\n## How to Use\n\n### Installation\nInstall the requirements via `pip install -r requirements.txt`.\n\n### Run Experiments\nRun the experiments via `python -m run_experiment -c config`, where `config` is a configuration file in `./configs/` directory.\nThe available values are `{config_mnist, config_cifar10, config_spotify, config_recogym, config_personalization}`, which could be specified to recreate each of the presented numerical experiments.\nOptionally, a custom experiment can be set up by changing or adding new configuration file.\n\n### Load Experiments\nAll previously performed experiments are stored in `./data/` directory and can be recreated by loading via `python -m run_experiment -l exp_name`, where `exp_name` is the name of the experiment as it is saved in `./data/`.\n\n### Results\n![Reward values](https://github.com/sukiboo/policy_entropy/assets/38059493/9ced0db4-ca67-4319-b464-1ad04aac6a70)\n![Entropy values](https://github.com/sukiboo/policy_entropy/assets/38059493/4a90feda-73dd-4809-89bc-772e9c4448de)\n\n\n\n## File Structure\n* `run_experiment.py` --- set up and run the experiment\n* `agent.py` --- set up selected RL agents\n* `environment.py` --- create the specified environment\n* `environments/` --- data required to set up various environments\n* `configs/` --- configuration files for the experiments\n* `data/` --- store data from previously run experiments\n* `images/` --- plots of various results from experiments\n* `visualization.py` --- save/load the experiment data, plot the results\n\n## License\nThis project is licensed under the MIT License.\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsukiboo%2Fpolicy_entropy","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsukiboo%2Fpolicy_entropy","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsukiboo%2Fpolicy_entropy/lists"}