Make-An-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusion
–Neural Information Processing Systems
Using low-dimensional demonstrations (such as agent behavior) to guide the generation of high-dimensional outputs (policy parameters) is a challenging problem.
Neural Information Processing Systems
Oct-9-2025, 20:54:16 GMT
- Country:
- Genre:
- Research Report > Experimental Study (0.46)
- Technology: