Downloads · 30 days
0
q-learning-FrozenLake-v1
muhrivandysetiawan/q-learning-FrozenLake-v1
q-learning-FrozenLake-v1 is a reinforcement learning model from muhrivandysetiawan. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product.
Pure NumPy Q-Learning on FrozenLake-v1 (non-slippery + slippery).
Access
Public
Updated Apr 6, 2026
Repo size
1.3 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.mp465.6 KB · 94%
At a glance
- Task
- Reinforcement Learning
- Access
- Public
- Created
- Apr 5, 2026
- Updated
- Apr 6, 2026
- SHA
- 0b5c1a01
Model card
From the Hugging Face model README
Q-Learning Agent -- FrozenLake-v1
Pure NumPy Q-Learning on FrozenLake-v1 (non-slippery + slippery).
Performance
| Mode | Score | Notes |
|---|---|---|
| Non-slippery | 1.0000 | Deterministic -- perfect |
| Slippery | 0.2135 | Stochastic -- harder |
Q-Table Insight
Non-slippery score of 1.0000 = agent finds optimal path 100% of time. Slippery score lower = stochastic transitions reduce Q-Learning effectiveness. This is exactly WHY Deep RL with function approximation exists.
Architecture (OOP)
QTable | EpsilonGreedyPolicy | QLearningEnv | QLearningTrainer
Project 2/12 -- Deep RL Portfolio Author: muhrivandysetiawan
- Task
- Reinforcement Learning
- Created
- Apr 5, 2026
- Updated
- Apr 6, 2026