{"id":18419587,"url":"https://github.com/redleader962/lecturedirigedrlimplementation","last_synced_at":"2026-04-30T15:31:08.281Z","repository":{"id":212891914,"uuid":"202403881","full_name":"RedLeader962/LectureDirigeDRLimplementation","owner":"RedLeader962","description":"Directed reading on  Deep Reinforcement Learning","archived":false,"fork":false,"pushed_at":"2023-12-17T03:29:15.000Z","size":65450,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-13T11:50:45.644Z","etag":null,"topics":["actor-critic","deep-reinforcement-learning","policy-gradient","soft-actor-critic","tensorflow","universite-laval"],"latest_commit_sha":null,"homepage":"","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/RedLeader962.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,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-08-14T18:22:40.000Z","updated_at":"2023-12-17T03:29:22.000Z","dependencies_parsed_at":null,"dependency_job_id":"3e1c5498-2bdb-4f55-904c-88f10fdc16d7","html_url":"https://github.com/RedLeader962/LectureDirigeDRLimplementation","commit_stats":null,"previous_names":["redleader962/lecturedirigedrlimplementation"],"tags_count":4,"template":false,"template_full_name":null,"purl":"pkg:github/RedLeader962/LectureDirigeDRLimplementation","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RedLeader962%2FLectureDirigeDRLimplementation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RedLeader962%2FLectureDirigeDRLimplementation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RedLeader962%2FLectureDirigeDRLimplementation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RedLeader962%2FLectureDirigeDRLimplementation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/RedLeader962","download_url":"https://codeload.github.com/RedLeader962/LectureDirigeDRLimplementation/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RedLeader962%2FLectureDirigeDRLimplementation/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32469344,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-30T13:12:12.517Z","status":"ssl_error","status_checked_at":"2026-04-30T13:12:06.837Z","response_time":57,"last_error":"SSL_read: 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":["actor-critic","deep-reinforcement-learning","policy-gradient","soft-actor-critic","tensorflow","universite-laval"],"created_at":"2024-11-06T04:17:31.353Z","updated_at":"2026-04-30T15:31:08.267Z","avatar_url":"https://github.com/RedLeader962.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"[![codecov](https://codecov.io/gh/RedLeader962/LectureDirigeDRLimplementation/branch/master/graph/badge.svg)](https://codecov.io/gh/RedLeader962/LectureDirigeDRLimplementation)\n\u003cimg src=https://sonarcloud.io/images/project_badges/sonarcloud-white.svg alt=\"sonarcloundlogo\" width=\"90\"\u003e\n\nRepository for the course IFT-7014: Directed reading on\n# Deep Reinforcement Learning \n\nby **Luc Coupal**,\nUniversité Laval,\nMontréal, QC, Canada,\n[Luc.Coupal.1@uLaval.ca](Luc.Coupal.1@uLaval.ca) \n\n#### Under the supervision of:\n\n**Professor Brahim Chaib-draa**,\nDirecteur du programme de baccalauréat en génie logiciel de l'Université Laval,\nQuébec, QC, Canada,\n[Brahim.Chaib-draa@ift.ulaval.ca](Brahim.Chaib-draa@ift.ulaval.ca)\n\n---\n![TaxonomyActorCritic](./visual/TaxonomyDRLgithub.png) \n\n\n### Essay on:\n- Maximum Entropy RL:\n  - **[Soft Actor-Critic](DRLimplementation/SoftActorCritic)**\n  - See my **blog post [_Soft Actor-Critic_ part 1: intuition and theoretical aspect](https://redleader962.github.io/blog/2020/SAC-part-1-distillarized/)** for more details on _SAC_ and _MaxEnt-RL_\n- Classical RL:\n  - **[Actor-Critic](DRLimplementation/ActorCritic)**\n  - **[Basic policy gradient](DRLimplementation/BasicPolicyGradient)**\n- **[A reflexion on design, architecture and implementation details](https://github.com/RedLeader962/LectureDirigeDRLimplementation/raw/master/Reflexion_on_design_and_architecture_LucCoupal_v1-1.pdf)**\n\n---\n\n![Trained agent in action](video/SAC_video/SAC_gif/SAC_postTraining_testOnHardLunar540p24fps.gif)\n\n[Watch mp4 video - Soft Actor-Critic Post training - Test run on 2X harder LunarLanderContinuous-v2 environment](video/SAC_video/SAC_postTraining_testOnHardLunar540p.mp4) \n\n---\n    \n### Install instruction:\n1) **Create \u0026 activate a new virtual environment** (I recommand using [conda](https://www.anaconda.com/distribution/), ... it's a walk in the park)\n    ```bash\n    conda create --name myNewVirtualEnvironmentName python=3.7\n    conda activate myNewVirtualEnvironmentName\n    ```\n2) **Clone** the GitHub repository \u0026 **install dependencies**:\n    ```bash\n    git clone https://github.com/RedLeader962/LectureDirigeDRLimplementation.git\n    cd LectureDirigeDRLimplementation\n    pip install -e .\n    ```\n    This will automaticaly install those **dependencies** in `myNewVirtualEnvironmentName` :\n\n        'gym\u003e=0.14.0'\n        'tensorflow\u003e=1.14.0,\u003c2.0',\n        'matplotlib\u003e=3.1.0',\n        'numpy\u003e=1.16.4',\n        'seaborn\u003e=0.9.0',\n        'pytest',\n    \n3) **Enjoy** DRL script\n\n---\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fredleader962%2Flecturedirigedrlimplementation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fredleader962%2Flecturedirigedrlimplementation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fredleader962%2Flecturedirigedrlimplementation/lists"}