policy
Reinforcement-Learning-Based-Robotic-Object-Picking-with-Koopman-Linear-Dynamics
Ankush0903 · IsaacLab
or hover any field below to flag it
Overview
Name
Reinforcement-Learning-Based-Robotic-Object-Picking-with-Koopman-Linear-Dynamics
Author
Ankush0903
Framework
IsaacLab
License
unknown
Skill type
manipulation
Evidence level
untested
Task description
RL-based robotic pick-and-place in NVIDIA Isaac Sim using PPO and Koopman linear model. Curriculum learning and parallel training (128–8192 environments) enhance efficiency. Achieves smoother, stable movements, compared to raw-state PPO. Data & scene generation and RL environment creation
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 Reinforcement-Learning-Based-Robotic-Object-Picking-with-Koopman-Linear-Dynamics yet.
Datasets that reference this policy
0No datasets reference Reinforcement-Learning-Based-Robotic-Object-Picking-with-Koopman-Linear-Dynamics yet.