policy
monte-carlo-methods
cooper-rm · PyTorch
or hover any field below to flag it
Overview
Name
monte-carlo-methods
Author
cooper-rm
Framework
PyTorch
License
unknown
Skill type
other
Evidence level
untested
Task description
This project implements first-visit Monte Carlo control with epsilon-greedy policies to train an RL agent to play Blackjack. The agent learns entirely from experience (model-free) using Gymnasium's Blackjack-v1 environment with Sutton & Barto rules.
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 yetCompatible environments
0No environments list monte-carlo-methods yet.
Datasets that reference this policy
0No datasets reference monte-carlo-methods yet.