Self-Supervised Exploration via Disagreement
International Conference on Machine Learning, pp. 5062-5071, 2019.
Instead of learning a single dynamics model, we propose an alternate exploration formulation based on ensemble of models as inspired by the classical active learning literature
Efficient exploration is a long-standing problem in sensorimotor learning. Major advances have been demonstrated in noise-free, non-stochastic domains such as video games and simulation. However, most of these formulations either get stuck in environments with stochastic dynamics or are too inefficient to be scalable to real robotics se...More
PPT (Upload PPT)