policy

lunar-transformer-il

Willian-Girao · PyTorch

or hover any field below to flag it

Overview

Name
lunar-transformer-il
Author
Willian-Girao
Framework
PyTorch
License
MIT
Skill type
other
Evidence level
untested
Task description
Exploring decoder-only transformer models for Imitation Learning (IL). The models are trained on data generated by Reinforcement Learning (RL) agents solving the Lunar Lander v3 environment of Gymnasium, a maintained fork of OpenAI’s Gym library, which is an API standard for RL with a diverse collec

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 lunar-transformer-il yet.

Datasets that reference this policy

0

No datasets reference lunar-transformer-il yet.