Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-free RL. (arXiv:2206.14057v1 [cs.LG])

While the primary goal of the exploration phase in reward-free reinforcement
learning (RF-RL) is to reduce the uncertainty in the estimated model with
minimum number of trajectories, in practice, the agent often needs to abide by
certain safety constraint at the same time. It remains unclear how such safe
exploration requirement would affect the corresponding sample complexity to
achieve the desired optimality of the obtained policy in planning. In this
work, we make a first attempt to answer this question. …

arxiv complexity exploration free lg rl