Algorithm 2 Online Infer most likely Goal for the Observations |
Require: : State and action spaces in the continuous domain, and policy evaluation networks Require: : a set of candidate goals Require: : an observation sequence
|
Algorithm 2 Online Infer most likely Goal for the Observations |
Require: : State and action spaces in the continuous domain, and policy evaluation networks Require: : a set of candidate goals Require: : an observation sequence
|