Exploration by Distributional Reinforcement Learning

Exploration by Distributional Reinforcement Learning

Yunhao Tang, Shipra Agrawal

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
Main track. Pages 2710-2716. https://doi.org/10.24963/ijcai.2018/376

We propose a framework based on distributional reinforcement learning and recent attempts to combine Bayesian parameter updates with deep reinforcement learning. We show that our proposed framework conceptually unifies multiple previous methods in exploration. We also derive a practical algorithm that achieves efficient exploration on challenging control tasks.
Keywords:
Machine Learning: Neural Networks
Machine Learning: Reinforcement Learning