Chunlok Lo
YOU?
Author Swipe
View article: Goal-Space Planning with Subgoal Models
Goal-Space Planning with Subgoal Models Open
This paper investigates a new approach to model-based reinforcement learning using background planning: mixing (approximate) dynamic programming updates and model-free updates, similar to the Dyna architecture. Background planning with lea…
View article: Continual Auxiliary Task Learning
Continual Auxiliary Task Learning Open
Learning auxiliary tasks, such as multiple predictions about the world, can provide many benefits to reinforcement learning systems. A variety of off-policy learning algorithms have been developed to learn such predictions, but as yet ther…
View article: Continual Auxiliary Task Learning
Continual Auxiliary Task Learning Open
Learning auxiliary tasks, such as multiple predictions about the world, can provide many benets to reinforcement learning systems. A variety of off-policy learning algorithms have been developed to learn such predictions, but as yet there …
View article: A Ramsey Type problem for highly connected subgraphs
A Ramsey Type problem for highly connected subgraphs Open
Bollobás and Gyárfás conjectured that for any $k, n \in \mathbb{Z}^+$ with $n > 4(k-1)$, every 2-edge-coloring of the complete graph on $n$ vertices leads to a $k$-connected monochromatic subgraph with at least $n-2k+2$ vertices. We find a…