policy

BlackJack-Model

harshitvarma05 · PyTorch

or hover any field below to flag it

Overview

Name
BlackJack-Model
Author
harshitvarma05
Framework
PyTorch
License
unknown
Skill type
other
Evidence level
untested
Task description
Trains and evaluates a Blackjack agent using PPO with vectorized environments and observation normalization. Includes model saving, stat export, and win-rate evaluation over 10,000 games.

Spaces

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

Links

HuggingFace repo
null
Paper (arXiv)
null

Compatible robots

20

Compatible environments

0

No environments list BlackJack-Model yet.

Datasets that reference this policy

0

No datasets reference BlackJack-Model yet.