Approximation Benefits of Policy Gradient Methods with Aggregated States. (arXiv:2007.11684v3 [cs.LG] UPDATED)

Web: http://arxiv.org/abs/2007.11684

Folklore suggests that policy gradient can be more robust to misspecification
than its relative, approximate policy iteration. This paper studies the case of
state-aggregated representations, where the state space is partitioned and
either the policy or value function approximation is held constant over
partitions. This paper shows a policy gradient method converges to a policy
whose regret per-period is bounded by $\epsilon$, the largest difference
between two elements of the state-action value function belonging to a common
partition. With the …

approximation arxiv benefits gradient lg policy