Constrained Policy Gradient Method for Safe and Fast Reinforcement Learning: a Neural Tangent Kernel Based Approach. (arXiv:2107.09139v2 [cs.LG] UPDATED)

This paper presents a constrained policy gradient algorithm. We introduce
constraints for safe learning with the following steps. First, learning is
slowed down (lazy learning) so that the episodic policy change can be computed
with the help of the policy gradient theorem and the neural tangent kernel.
Then, this enables us the evaluation of the policy at arbitrary states too. In
the same spirit, learning can be guided, ensuring safety via augmenting episode
batches with states where the desired action …

arxiv gradient kernel learning policy reinforcement learning