policy

ESN-GRL-based-Generative-Adversarial-Imitation-Learning

frezazadeh · PyTorch

or hover any field below to flag it

Overview

Name
ESN-GRL-based-Generative-Adversarial-Imitation-Learning
Author
frezazadeh
Framework
PyTorch
License
MIT
Skill type
other
Evidence level
untested
Task description
This repository implements a two-stage imitation learning framework. First, a graph-based reinforcement learning (GRL) agent is trained as an expert policy. Then, Generative Adversarial Imitation Learning (GAIL) uses the expert’s demonstrations to train a new policy that imitates the expert without

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 ESN-GRL-based-Generative-Adversarial-Imitation-Learning yet.

Datasets that reference this policy

0

No datasets reference ESN-GRL-based-Generative-Adversarial-Imitation-Learning yet.