Noisy Networks for Exploration

ICLR 2018 Meire FortunatoMohammad Gheshlaghi AzarBilal PiotJacob MenickIan OsbandAlex GravesVlad MnihRemi MunosDemis HassabisOlivier PietquinCharles BlundellShane Legg

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... (read more)

PDF Abstract

Evaluation results from the paper


  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.