Downloads · 30 days
0
briscola_dqn
paolvz/briscola_dqn
briscola_dqn is a machine learning model from paolvz. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Access
Public
Updated Dec 2, 2023
Repo size
1.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt-4750001.8 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Dec 2, 2023
- Updated
- Dec 2, 2023
- SHA
- 1669257f
Model card
From the Hugging Face model README
Training an AI Agent in th Game of Briscola
Checkpoint models for 2vs2 briscola card game trained with Deep Q Networks Algorithm:
- only-round-reward model (best model)
- only-game-reward model (only for analysis)
Only-round-reward performances (best model):
~92% win rate vs random agent
~37% win rate vs human agent
More info at https://github.com/flaccagora/Briscola/
- License
- apache-2.0
- Created
- Dec 2, 2023
- Updated
- Dec 2, 2023