{"id":30957275,"url":"https://github.com/bdrhnsen/rl_visualizer","last_synced_at":"2026-05-17T00:41:02.849Z","repository":{"id":261144606,"uuid":"883416600","full_name":"bdrhnsen/rl_visualizer","owner":"bdrhnsen","description":"Visualize reinforcement learning model action probabilities (values of state action pairs)","archived":false,"fork":false,"pushed_at":"2025-01-25T17:44:42.000Z","size":7,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-08-19T14:36:03.636Z","etag":null,"topics":["reinforcement-learning","stable-baselines3","state-action-reward-state-action","visualization"],"latest_commit_sha":null,"homepage":"","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/bdrhnsen.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":"2024-11-04T23:34:37.000Z","updated_at":"2025-01-25T17:44:46.000Z","dependencies_parsed_at":null,"dependency_job_id":"3884d690-1cec-407d-8c83-70d1abe704c2","html_url":"https://github.com/bdrhnsen/rl_visualizer","commit_stats":null,"previous_names":["bdrhnsen/rl_visualizer"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/bdrhnsen/rl_visualizer","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bdrhnsen%2Frl_visualizer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bdrhnsen%2Frl_visualizer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bdrhnsen%2Frl_visualizer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bdrhnsen%2Frl_visualizer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bdrhnsen","download_url":"https://codeload.github.com/bdrhnsen/rl_visualizer/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bdrhnsen%2Frl_visualizer/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274648319,"owners_count":25324299,"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","status":"online","status_checked_at":"2025-09-11T02:00:13.660Z","response_time":74,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["reinforcement-learning","stable-baselines3","state-action-reward-state-action","visualization"],"created_at":"2025-09-11T13:45:10.805Z","updated_at":"2026-05-17T00:40:57.831Z","avatar_url":"https://github.com/bdrhnsen.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# RL Visualizer\n\nRL Visualizer is a Python package for visualizing action probabilities, entropy, and rewards in reinforcement learning models.\n\n## Features\n\n- Visualize action probabilities as bar charts\n- Track entropy to monitor model uncertainty\n- Plot per-step rewards within a single episode\n- Compatible with Gym and Gymnasium environments\n\n## Installation\n\n```bash\npip install rl-visualizer\n```\n## Example\n\n- Here you can see what rl_visualizer do in action:\n- This is a custom highway simulated environment in Gymasium format\n- Action space: is defined with this\n```python\n- Enum class Action(Enum):\n    NO_ACTION = 0\n    CHANGE_LANE_RIGHT = 1\n    CHANGE_LANE_LEFT = 2\n    ACCELERATE = 3\n    DECELERATE = 4\n    EMERGENCY_BRAKE = 5\n ```\n - Given reward for driving between 75km/h and 104km/h (max reward for 104km/h and driving not on leftmost lane)\n - Given extra reward if driving not in the leftmost lane\n - Given negative reward for near collisions and collisions. Near collision is calculated by ttc \n![Image](https://github.com/user-attachments/assets/72280c79-4f85-4391-9f2b-6a1eca5b29dc)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbdrhnsen%2Frl_visualizer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbdrhnsen%2Frl_visualizer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbdrhnsen%2Frl_visualizer/lists"}