Downloads · 30 days
0
q-FrozenLake-v1-4x4-noSlippery
crossroderick/q-FrozenLake-v1-4x4-noSlippery
q-FrozenLake-v1-4x4-noSlippery is a reinforcement learning model from crossroderick. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product.
This is a trained model of a Q-Learning agent playing FrozenLake-v1 .
Access
Public
Updated Feb 22, 2024
Repo size
1.8 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.mp431.1 KB · 90%
At a glance
- Task
- Reinforcement Learning
- Access
- Public
- Created
- Feb 22, 2024
- Updated
- Feb 22, 2024
- SHA
- 5a654685
Model card
From the Hugging Face model README
Q-Learning Agent playing FrozenLake-v1
This is a trained model of a Q-Learning agent playing FrozenLake-v1 .
Usage
model = load_from_hub(repo_id = "crossroderick/q-FrozenLake-v1-4x4-noSlippery", filename = "q-learning.pkl")
This particular model was trained on the default version of FrozenLake-v1 in a 4x4 setting, so don't forget to set is_slippery = False and
specify map_name when loading the environment, such as:
env = gym.make(model["env_id"], map_name = "4x4", is_slippery = False)
- Task
- Reinforcement Learning
- Created
- Feb 22, 2024
- Updated
- Feb 22, 2024