ART/ATK: A research platform for assessing and mitigating the sim-to-real gap in robotics and autonomous vehicle engineering

Safe exploration in model-based reinforcement learning using control barrier functions

“…Our work is based on Safety Augmented Value Estimation from Demonstrations (SAVED) [6,7,8,9,10]. SAVED is a sample-efficient method that can consistently complete tasks with complex safety constraints using only non-expert, sub-optimal demonstrations and sparse rewards from simple supervision identifying task completion.…”