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/
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no library tag.