Domains as Objectives: Multi-Domain Reinforcement Learning with Convex-Coverage Set Learning for Domain Uncertainty Awareness
Wendyam Eric Lionel Ilboudo,Taisuke Kobayashi,Takamitsu Matsubara,Wendyam Eric Lionel Ilboudo,Taisuke Kobayashi,Takamitsu Matsubara
Domain randomization (DR) is a powerful framework that has allowed the transfer of policies from randomized domain (a.k.a. simulation) to real robots with little to no retraining requirement. However, because the policy has to perform well for many different domain conditions, DR tends to produce sub-optimal policies that can be too conservative on the target real system. This problem is further e...
