Safe Reinforcement Learning in a Simulated Robotic Arm

arXiv:2312.09468v2 Announce Type: replace-cross
Abstract: Reinforcement learning (RL) agents need to explore their environments in order to learn optimal policies. In many environments and tasks, safety is of critical importance. The widespread use of simulators offers a number of advantages, including safe exploration which will be inevitable in cases when RL systems need to be trained directly in the physical environment (e.g. in human-robot interaction). The popular Safety Gym library offers three mobile agent types that can learn goal-directed tasks …

abstract advantages agents arm arxiv cases cs.ai cs.lg cs.ro environments exploration explore importance learn reinforcement reinforcement learning robotic robotic arm safety systems tasks type will