policy

marineqlean

highcansavci · PyTorch

or hover any field below to flag it

Overview

Name
marineqlean
Author
highcansavci
Framework
PyTorch
License
unknown
Skill type
manipulation
Evidence level
untested
Task description
MarineQlean is a multi-agent system that uses advanced reinforcement learning techniques to coordinate autonomous vessels for efficient marine waste collection. The project implements the COMA (Counterfactual Multi-Agent Policy Gradients) algorithm with curriculum learning to train agents in collect

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 marineqlean yet.

Datasets that reference this policy

0

No datasets reference marineqlean yet.