{"id":24874807,"url":"https://github.com/mohankrishnagr/reinforcement-learning-taxi-v3","last_synced_at":"2026-04-12T23:54:35.950Z","repository":{"id":273111997,"uuid":"918726963","full_name":"MohanKrishnaGR/Reinforcement-Learning-Taxi-v3","owner":"MohanKrishnaGR","description":" A comprehensive solution to the Classic Taxi Problem using Reinforcement Learning (RL) and OpenAI Gym (Taxi-v3). This repository includes Python code for Q-learning implementation, a detailed presentation, and visualizations to demonstrate the agent's learning process. Perfect for anyone exploring RL concepts, Q-learning, or Gym environments.","archived":false,"fork":false,"pushed_at":"2025-01-18T18:17:16.000Z","size":1122,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-27T02:16:06.410Z","etag":null,"topics":["artificial-intelligence","openai-gym","python","q-learning","reinforcement-learning","rl-algorithms","taxi-problem"],"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/MohanKrishnaGR.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":"2025-01-18T17:43:08.000Z","updated_at":"2025-01-18T18:20:12.000Z","dependencies_parsed_at":"2025-01-18T19:24:12.304Z","dependency_job_id":"8ae947b8-7ed9-41b7-8c02-e33168d8e9fc","html_url":"https://github.com/MohanKrishnaGR/Reinforcement-Learning-Taxi-v3","commit_stats":null,"previous_names":["mohankrishnagr/reinforcement-learning-taxi-v3"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/MohanKrishnaGR/Reinforcement-Learning-Taxi-v3","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MohanKrishnaGR%2FReinforcement-Learning-Taxi-v3","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MohanKrishnaGR%2FReinforcement-Learning-Taxi-v3/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MohanKrishnaGR%2FReinforcement-Learning-Taxi-v3/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MohanKrishnaGR%2FReinforcement-Learning-Taxi-v3/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MohanKrishnaGR","download_url":"https://codeload.github.com/MohanKrishnaGR/Reinforcement-Learning-Taxi-v3/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MohanKrishnaGR%2FReinforcement-Learning-Taxi-v3/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":270602456,"owners_count":24614260,"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":"2025-08-15T02:00:12.559Z","response_time":110,"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":["artificial-intelligence","openai-gym","python","q-learning","reinforcement-learning","rl-algorithms","taxi-problem"],"created_at":"2025-02-01T07:28:46.240Z","updated_at":"2026-04-12T23:54:30.918Z","avatar_url":"https://github.com/MohanKrishnaGR.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Reinforcement-Learning-Taxi-v3\nThis repository tackles the Taxi-v3 problem from OpenAI Gym, a classic gridworld challenge in Reinforcement Learning (RL). The project demonstrates:\n\n* Training an RL agent using the Q-learning algorithm.\n* Visualization of the environment with step-by-step agent actions.\n* Insights into the reward system, exploration-exploitation strategies, and training hyperparameters.\n\nWhether you're a student, researcher, or RL enthusiast, this repository provides an accessible starting point for learning RL concepts and applying them in simulated environments.\n\n# 🚕 Classic Gym's Taxi Problem: A Reinforcement Learning Case Study\n\nHere's an demonstration on how to solve the **Taxi-v3 problem** using **Reinforcement Learning (RL)**. The project explores Q-Learning, a model-free RL algorithm, and uses **OpenAI Gym** to simulate the Taxi environment. (Refer slides)\n\n### Problem visualization:\n\n![Video](./av/taxi_problem_gif.gif)\n\n\n## 📂 Repository Contents\n- **Code**: Python implementation for training and testing the taxi agent using Q-learning.\n- **Presentation**: A detailed PowerPoint presentation explaining the problem, solution approach, and results.\n- **Environment Setup**: Instructions to set up the environment for running the code.\n\n---\n\n## 🌟 Problem Overview\nThe Taxi problem involves navigating a taxi through a grid to:\n1. **Pick up** a passenger from a designated location.\n2. **Drop off** the passenger at the destination.\n3. Optimize actions to maximize rewards.\n\n### **Key Concepts**\n- **State Space**: Taxi position, passenger location, and destination.\n- **Action Space**: Move (North, South, East, West), Pick Up, Drop Off.\n- **Rewards**: Positive for successful drops, negative for invalid actions, and step penalties.\n\n---\n\n## 🛠️ Getting Started\n\n### Prerequisites\n1. **Python** (\u003e=3.7)\n2. **OpenAI Gym** (tested with version 0.16.0)\n3. **NumPy**\n\n### Installation\n1. Clone the repository:\n   ```bash\n   git clone https://github.com/MohanKrishnaGR/Reinforcement-Learning-Taxi-v3.git\n   cd Reinforcement-Learning-Taxi-v3 \n   ```\n\n2. Install dependencies:\n    ```bash\n    pip install gym==0.16 numpy\n    ```\n\n---\n## 🚀 Running the Code\n1. Run the Python script:\n    ```bash\n    python taxi_problem.py\n    ```\n2. Watch the agent learn and test the trained model.\n---\n## 📊 Results\n\n* **Training**: The agent learns the optimal policy over multiple episodes using the Q-learning algorithm.\n\n* **Testing**: The trained agent successfully navigates the gridworld to maximize rewards.\n\n* **Visualization**: The environment is rendered step-by-step to visualize the agent’s behavior after training.\n---\n## 📜 Presentation\nThe PowerPoint presentation provides:\n\n* An introduction to Reinforcement Learning and the Taxi Problem.\n* A walkthrough of Q-learning and its application to the problem.\n* Results with key takeaways.\n---\n### End Note\n\nThank you for your interest in this project! We welcome any feedback. Feel free to reach out to us.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmohankrishnagr%2Freinforcement-learning-taxi-v3","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmohankrishnagr%2Freinforcement-learning-taxi-v3","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmohankrishnagr%2Freinforcement-learning-taxi-v3/lists"}