Exploration by Distributional Reinforcement Learning
arXiv:1805.01907v234 citations
Originality Incremental advance
AI Analysis
This work addresses exploration challenges in reinforcement learning for AI agents, presenting a novel but incremental improvement over existing techniques.
The paper tackles the problem of efficient exploration in reinforcement learning by proposing a framework that unifies previous methods and achieves strong performance on challenging control tasks.
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.