metadata
tags:
- reinforcement-learning
- Taxi-v3
- q-learning
- deep-rl-course
model-index:
- name: q-Taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.69 +/- 2.87
name: mean_reward
Q-Learning Agent playing Taxi-v3
This is a trained model of a Tabular Q-Learning agent playing Taxi-v3.
The agent was trained and evaluated directly using the Bellman optimality update equation.
Evaluation Results
- Mean Reward:
7.69 +/- 2.87(Passing threshold: $\ge 4.0$) - Number of Evaluation Episodes: 100
- Model weights: Saved in
q_table.pkl
Trained and submitted by Subhash3008.