Simple q-learning implementation for taxi-v3 environment of Open AI gym.
-
Updated
Feb 16, 2022 - Python
#
taxi-v3
Here are 23 public repositories matching this topic...
In this paper we re-define MAXQ and the taxi environment and Implement them in R. We then apply Qlearning to the same problem. Our conclusion is that MAXQ works as good as Qlearning for this problem. Our aim is illustrate the advantages of using hierarchical reinforcement learning methods.
-
Updated
Aug 20, 2021 - R
In this project, we tried two different Learning Algorithms for Hierarchical RL on the Taxi-v3 environment from OpenAI gym. SMDP Q-Learning and Intra Option Q-Learning and contrasted them with two other methods that involve hardcoding based on human understanding. We conclude that the solutions learnt by machine are way superior than humans for …
machine-learning reinforcement-learning openai-gym semi-markov-decision-process q-learning-algorithm taxi-v3 opengy
-
Updated
Jul 31, 2022 - Jupyter Notebook
A simple Q-learning implementation in OpenAI Gym's "Taxi-v3" environment
-
Updated
Sep 23, 2024 - Python
Going through the Hugging Face Deep Reinforcement Learning course.
q-learning godot atari vizdoom imitation-learning gymnasium actor-critic deep-q-learning deep-rl ppo policy-gradients unity-ml-agents optuna huggingface multi-agent-rl taxi-v3 huggy stable-baselines3 frozenlake-v1 lunarlander-v3
-
Updated
Jun 3, 2026 - Jupyter Notebook
Implementation of Q-learning Algorithm on FrozenLake and Taxi environments
-
Updated
Apr 1, 2024 - Jupyter Notebook
OpenAI's Taxi-v3 environment.
-
Updated
Apr 20, 2020 - Python
A Reinforcement Learning project solving the Gymnasium Taxi-v3 environment. It implements and compares tabular Q-Learning with a Deep Q-Network (DQN). The agent is trained to efficiently pick up and drop off a passenger in the fewest possible moves.
-
Updated
Jul 29, 2026 - Python
Epitech Project - Reinforcement learning agents solving the Taxi-v3 environment from Gymnasium.
-
Updated
Jul 30, 2026 - Python
Taksi-Yolcu problemi için Pekiştirmeli Öğrenme (RL) Ajanı
-
Updated
Nov 28, 2025 - Python
OpenAI Gym (Q-learning)
-
Updated
May 12, 2020 - Jupyter Notebook
Q_LEARNING_EG_SARSA_TAXI
-
Updated
Jul 28, 2024 - Jupyter Notebook
My solution to the OpenAI Taxi-v3 task
-
Updated
Jul 11, 2022 - Jupyter Notebook
Finding the optimal route that a taxi has to take to pick up and drop a customer
-
Updated
Jul 4, 2024 - Jupyter Notebook
Comparing SARSA, Q-Learning, and Double Q-Learning on Cliff Walking and Taxi-V3 Tasks
reinforcement-learning qlearning sarsa temporal-differencing-learning double-q-learning taxi-v3 cliff-walking-problem
-
Updated
Jun 24, 2026 - Jupyter Notebook
🚕 This repository contains the implementation of a Reinforcement Learning agent capable of solving the "Taxi" problem from the OpenAI Gym environment.
-
Updated
Mar 6, 2026 - Jupyter Notebook
Scripts to test the influence of learning rate and discount rate on q-learning algorithms using OpenAI Gym's Taxi environment
-
Updated
Dec 27, 2022 - Python
This project simulates an intelligent taxi system using Q-learning in the Taxi-v3 environment, enhanced with traffic delays, weather penalties, and energy constraints. It demonstrates how reinforcement learning can adapt to real-world challenges while visualizing taxi rides for better understanding.
python reinforcement-learning openai-gym openai autonomous-vehicles qlearning-algorithm pandas-library taxi-v3
-
Updated
Sep 12, 2025 - Jupyter Notebook
Compare q-learning, SARSA and Expected SARSA to solve AI gym's Taxi-v3 environment
reinforcement-learning expected-sarsa gym-environment sarsa-learning q-learning-vs-sarsa q-learning-algorithm taxi-v3
-
Updated
Oct 25, 2022 - Jupyter Notebook
Improve this page
Add a description, image, and links to the taxi-v3 topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the taxi-v3 topic, visit your repo's landing page and select "manage topics."