File:1-GSP.png

From statwiki
Revision as of 23:45, 31 October 2018 by Vrajendr (talk | contribs) (The goal-conditioned skill policy (GSP) takes as input the current and goal observations and outputs an action sequence that would lead to that goal. We compare the performance of the following GSP models: (a) Simple inverse model; (b) Mutli-step GSP w...)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search
The printable version is no longer supported and may have rendering errors. Please update your browser bookmarks and please use the default browser print function instead.

Original file(3,892 × 1,976 pixels, file size: 382 KB, MIME type: image/png)

The goal-conditioned skill policy (GSP) takes as input the current and goal observations and outputs an action sequence that would lead to that goal. We compare the performance of the following GSP models: (a) Simple inverse model; (b) Mutli-step GSP with previous action history; (c) Mutli-step GSP with previous action history and a forward model as regularizer, but no forward consistency; (d) Mutli-step GSP with forward consistency loss proposed in this work.

File history

Click on a date/time to view the file as it appeared at that time.

Date/TimeThumbnailDimensionsUserComment
current23:45, 31 October 2018Thumbnail for version as of 23:45, 31 October 20183,892 × 1,976 (382 KB)Vrajendr (talk | contribs)The goal-conditioned skill policy (GSP) takes as input the current and goal observations and outputs an action sequence that would lead to that goal. We compare the performance of the following GSP models: (a) Simple inverse model; (b) Mutli-step GSP w...

The following page uses this file:

Metadata