Search Results for author:
Found 4 papers, 0 papers with code
Asymptotically Optimal Pure Exploration for Infinite-Armed Bandits
For fixed budget, we show the asymptotically optimal sample complexity as $\delta\to 0$ is $c^{-1}\log(1/\delta)\big(\log\log(1/\delta)\big)^2$ to leading order.
Provably More Efficient Q-Learning in the One-Sided-Feedback/Full-Feedback Settings
Motivated by the episodic version of the classical inventory control problem, we propose a new Q-learning-based algorithm, Elimination-Based Half-Q-Learning (HQL), that enjoys improved efficiency over existing algorithms for a wide variety of problems in the one-sided-feedback setting.
Efficient Entropy for Policy Gradient with Multidimensional Action Space
We develop several novel unbiased estimators for the entropy bonus and its gradient.
Policy Gradient For Multidimensional Action Spaces: Action Sampling and Entropy Bonus
In the case of high-dimensional action spaces, calculating the entropy and the gradient of the entropy requires enumerating all the actions in the action space and running forward and backpropagation for each action, which may be computationally infeasible.
