arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2007.13442cs.LGstat.ML
收藏

强化学习中用于纯探索的快速主动学习

Fast active learning for pure exploration in reinforcement learning

Inria(法国国家信息与自动化研究所);Universitat Pompeu Fabra(庞培法布拉大学);CNRS(法国国家科学研究中心);ULille(里尔大学);Renault(雷诺集团);DeepMind(深度思维公司)

Pierre Ménard, Omar Darwiche Domingues, Anders Jonsson, Emilie Kaufmann, Edouard Leurent, Michal Valko

摘要:

现实环境通常为代理提供非常有限的反馈。当环境最初是未知的,反馈,在一开始,可以是完全没有的,和代理可能会首先选择把他们所有的努力有效地探索。探索仍然是一个挑战,虽然它已经解决了许多手工调整的算法,一方面具有不同程度的通用性,另一方面有一些理论支持的探索策略。他们中的许多人体现了内在的动机,特别是探索奖金。探索奖励的一个常见经验法则是使用$1/\sqrt{n}$奖励,它被添加到奖励的经验估计中,其中$n$是访问该特定状态(或状态-动作对)的次数。我们发现,令人惊讶的是,对于一个纯粹的探索目标的奖励免费的探索,奖金规模与$1/n$带来更快的学习率,提高已知的上限方面的依赖地平线$H$。此外,我们表明,与改进的停止时间的分析,我们可以提高一个因素$H$的最佳策略识别设置,这是另一个纯粹的探索目标,其中环境提供奖励,但代理是不是惩罚其行为在探索阶段的样本复杂性。

英文摘要:

Realistic environments often provide agents with very limited feedback. When the environment is initially unknown, the feedback, in the beginning, can be completely absent, and the agents may first choose to devote all their effort on exploring efficiently. The exploration remains a challenge while it has been addressed with many hand-tuned heuristics with different levels of generality on one side, and a few theoretically-backed exploration strategies on the other. Many of them are incarnated by intrinsic motivation and in particular explorations bonuses. A common rule of thumb for exploration bonuses is to use $1/\sqrt{n}$ bonus that is added to the empirical estimates of the reward, where $n$ is a number of times this particular state (or a state-action pair) was visited. We show that, surprisingly, for a pure-exploration objective of reward-free exploration, bonuses that scale with $1/n$ bring faster learning rates, improving the known upper bounds with respect to the dependence on the horizon $H$. Furthermore, we show that with an improved analysis of the stopping time, we can improve by a factor $H$ the sample complexity in the best-policy identification setting, which is another pure-exploration objective, where the environment provides rewards but the agent is not penalized for its behavior during the exploration phase.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑