policy

scopa-master

WildPino · PyTorch

or hover any field below to flag it

Overview

Name
scopa-master
Author
WildPino
Framework
PyTorch
License
unknown
Skill type
other
Evidence level
untested
Task description
This repository implements a Reinforcement Learning (RL) environment for the Italian card game Scopa, using the gymnasium library and Proximal Policy Optimization (PPO). The aim is to train an AI agent to master Scopa through self-play and state observation, handling unique mechanics like the two-ph

Spaces

Action space
other · 0-dim · 0Hz
Observation space
  • type: other

Links

HuggingFace repo
null
Paper (arXiv)
null

Compatible robots

3+17 mentioned but not in catalog yet

Compatible environments

0

No environments list scopa-master yet.

Datasets that reference this policy

0

No datasets reference scopa-master yet.