Efficiently Learning Small Policies for Locomotion and Manipulation
Shashank Hegde,Gaurav S. Sukhatme,Shashank Hegde,Gaurav S. Sukhatme
Neural control of memory-constrained, agile robots requires small, yet highly performant models. We leverage graph hyper networks to learn graph hyper policies trained with off-policy reinforcement learning resulting in networks that are two orders of magnitude smaller than commonly used networks yet encode policies comparable to those encoded by much larger networks trained on the same task. We s...
