We introduce NoisyNet, a deep reinforcement learning agent with parametric noise added to its weights, and show that the induced stochasticity of the agent's policy can be used to aid efficient exploration. The parameters of the noise are learned with gradient descent along with the remaining network weights. NoisyNet is straightforward to implement and adds little computational overhead. We find that replacing the conventional exploration heuristics for A3C, DQN and dueling agents (entropy reward and ϵ-greedy respectively) with NoisyNet yields substantially higher scores for a wide range of Atari games, in some cases advancing the agent from sub to super-human performance.
@article{arxiv.1706.10295,
title = {Noisy Networks for Exploration},
author = {Meire Fortunato and Mohammad Gheshlaghi Azar and Bilal Piot and Jacob Menick and Ian Osband and Alex Graves and Vlad Mnih and Remi Munos and Demis Hassabis and Olivier Pietquin and Charles Blundell and Shane Legg},
journal= {arXiv preprint arXiv:1706.10295},
year = {2019}
}