Random Network Distillation: A New Take on Curiosity-Driven Learning
Dataiku
NOVEMBER 12, 2020
Last time , we learned about curiosity in deep reinforcement learning. The idea of curiosity-driven learning is to build a reward function that is intrinsic to the agent (generated by the agent itself). That is, the agent is a self-learner, as he is both the student and its own feedback teacher.
Let's personalize your content