BriefGPT.xyz
Feb, 2023
稀疏奖励多智能体强化学习中基于好奇心的探索
Curiosity-driven Exploration in Sparse-reward Multi-agent Reinforcement Learning
HTML
PDF
Jiong Li, Pratik Gajane
TL;DR
本研究讨论了在稀疏奖励情况下深度强化学习方法的稀疏性会影响其样本效率，而内在动机学习是一种解决稀疏奖励问题的有效方法，文章将内在动机学习方法与Go-Explore框架相结合提出了一种叫I-Go-Explore的方法以缓解其所带来的detachments问题。
Abstract
sparsity of rewards
while applying a
deep reinforcement learning
method negatively affects its sample-efficiency. A viable solution to deal with the
→