Parameter Space Noise for Exploration

ICLR 2018 Matthias PlappertRein HouthooftPrafulla DhariwalSzymon SidorRichard Y. ChenXi ChenTamim AsfourPieter AbbeelMarcin Andrychowicz

Deep reinforcement learning (RL) methods generally engage in exploratory behavior through noise injection in the action space. An alternative is to add noise directly to the agent's parameters, which can lead to more consistent exploration and a richer set of behaviors... (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.