Conservative safety critics for exploration
Safe exploration presents a major challenge in reinforcement learning (RL): when active
data collection requires deploying partially trained policies, we must ensure that these …
data collection requires deploying partially trained policies, we must ensure that these …
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 …
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 …
data collection requires deploying partially trained policies, we must ensure that these …