Logarithmic Regret for Learning Linear Quadratic Regulators Efficiently [article]

Asaf Cassel
2020 arXiv   pre-print
We consider the problem of learning in Linear Quadratic Control systems whose transition parameters are initially unknown. Recent results in this setting have demonstrated efficient learning algorithms with regret growing with the square root of the number of decision steps. We present new efficient algorithms that achieve, perhaps surprisingly, regret that scales only (poly)logarithmically with the number of steps in two scenarios: when only the state transition matrix A is unknown, and when
more » ... ly the state-action transition matrix B is unknown and the optimal policy satisfies a certain non-degeneracy condition. On the other hand, we give a lower bound that shows that when the latter condition is violated, square root regret is unavoidable.
arXiv:2002.08095v2 fatcat:7ojyorwaufbyrjxa6hgsmt7vta