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 1903.06151cs.LGcs.AIstat.ML
收藏

基于反馈探索的深度强化学习

Deep Reinforcement Learning with Feedback-based Exploration

Delft University of Technology(代尔夫特理工大学)

Jan Scholten, Daan Wout, Carlos Celemin, Jens Kober

摘要:

深度强化学习使人们能够控制日益复杂和高维的问题。然而,在获得合理的性能之前需要大量的数据,这阻碍了其广泛的应用。我们采用二进制校正反馈作为一种通用和直观的方式,将人类的直觉和领域知识的无模型机器学习。策略中的不确定性和校正反馈直接在动作空间中组合为概率条件探索。因此,可以避免大部分无知的学习过程。我们证明了所提出的方法,预测概率合并的政策(PPMP),结合DDPG。在OpenAI Gym的连续控制问题的实验中,我们在样本效率、最终性能和对错误反馈的鲁棒性方面都有了大幅提高,无论是人为反馈还是合成反馈。此外,我们还展示了超出所展示知识的解决方案。

英文摘要:

Deep Reinforcement Learning has enabled the control of increasingly complex and high-dimensional problems. However, the need of vast amounts of data before reasonable performance is attained prevents its widespread application. We employ binary corrective feedback as a general and intuitive manner to incorporate human intuition and domain knowledge in model-free machine learning. The uncertainty in the policy and the corrective feedback is combined directly in the action space as probabilistic conditional exploration. As a result, the greatest part of the otherwise ignorant learning process can be avoided. We demonstrate the proposed method, Predictive Probabilistic Merging of Policies (PPMP), in combination with DDPG. In experiments on continuous control problems of the OpenAI Gym, we achieve drastic improvements in sample efficiency, final performance, and robustness to erroneous feedback, both for human and synthetic feedback. Additionally, we show solutions beyond the demonstrated knowledge.

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。

↑