Mattizza's picture
add Taxi_v3, 1,000,000 steps
b218cbb verified
metadata
tags:
  - Taxi-v3
  - q-learning
  - reinforcement-learning
  - custom-implementation
model-index:
  - name: Taxi-v3_v0_DeepRLCourse
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: Taxi-v3
          type: Taxi-v3
        metrics:
          - type: mean_reward
            value: 7.56 +/- 2.71
            name: mean_reward
            verified: false

This is a trained model of a Q-Learning agent playing FrozenLake-v1 with no slippery. It leverages the Gymnasium environment, useful to get acquainted with Q-Learning. Very easy but useful to understand the basic concepts.

Q-Learning Agent playing1 Taxi-v3

This is a trained model of a Q-Learning agent playing Taxi-v3. It leverages the Gymnasium environment, useful to get acquainted with Q-Learning. Very easy but useful to understand the basic concepts.

Usage

import gymnasium as gym
from huggingface_sb3 import load_from_hub

model = load_from_hub(repo_id="Mattizza/Taxi-v3_v0_DeepRLCourse", filename="q-learning.pkl")
env = gym.make(model["env_id"])