Conservative safety critics for exploration

H Bharadhwaj, A Kumar, N Rhinehart, S Levine… - arXiv preprint arXiv …, 2020 - arxiv.org
Safe exploration presents a major challenge in reinforcement learning (RL): when active
data collection requires deploying partially trained policies, we must ensure that these …
被引用次数：132 相关文章 HTML 版

Conservative Safety Critics for Exploration

H Bharadhwaj, A Kumar, N Rhinehart, S Levine… - … Conference on Learning … - openreview.net
Safe exploration presents a major challenge in reinforcement learning (RL): when active
data collection requires deploying partially trained policies, we must ensure that these …

Conservative Safety Critics for Exploration

H Bharadhwaj, A Kumar, N Rhinehart… - arXiv e …, 2020 - ui.adsabs.harvard.edu
Safe exploration presents a major challenge in reinforcement learning (RL): when active
data collection requires deploying partially trained policies, we must ensure that these …