Learn More
In the HRL (hierarchical reinforcement learning) field, there are three main methods such as HAMs (hierarchical abstract machines), options, MAXQ. These methods all rely on the theory of SMDPs. While the SMDP framework allows us to directly model the high-level actions that take varying amounts of time, it provides little in the way of concrete(More)
In the HRL field, there are several main methods such as HAMs, options, MAXQ. These methods all rely on the theory of SMDPs. However, SMDPs does not specify how the overall task can be decomposed into a collection of subtasks. This paper introduces the concept of “policy-coupled” SMDPs into HAMs. It defines the concept of HAM-decomposable(More)
Lower resolution is the main shortcoming for geometrical model. Mesh smoothing is a basic method for turning a coarse and lower resolution model into a smooth one. The paper proposed a mesh smoothing method for parameterized geometrical body model based on the Loop subdivision. A smooth surface can be expressed with a lot of subdivision control meshes that(More)
The paper presents a template modeler for modeling individualization, realistic body surface. A new body shape is easily generated by modifying a template model with some dressing parameters. The problem is approached by some fitted silhouettes that are devoted to the generation of appropriate shape and proportion of the body geometry with inputting the(More)
  • 1