policy
CrowdRL
FabianPlum · PyTorch
or hover any field below to flag it
Overview
Name
CrowdRL
Author
FabianPlum
Framework
PyTorch
License
MIT
Skill type
locomotion
Evidence level
untested
Task description
MARL-learned pedestrian navigation policies trained in procedural 2D environments, validated against IAS-7 experiment data. Augments hand-crafted locomotion models in JuPedSim.
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 CrowdRL yet.
Datasets that reference this policy
0No datasets reference CrowdRL yet.