Time-regularized interrupting options

By Daniel Jaymin Mankowitz, Timothy A. Mann, Shie Mannor. 2014

23 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

A Deep Hierarchical Approach to Lifelong Learning in Minecraft (2016, background): “, 1999) and experimentally (Mann & Mannor, 2013; Mankowitz et al., 2014) to speed up the convergence rate of RL algorithms.”
Variational Intrinsic Control (2016, background): “…to option learning where the goal is to ﬁnd a small number of options that are useful for a particular task (Sutton et al., 1999; McGovern & Barto, 2001; Stolle & Precup, 2002; Silver & Ciosek, 2012; Kulkarni et al., 2016; Mankowitz et al., 2014; Vezhnevets et al., 2016; Bacon & Precup, 2015).”
Spatio-Temporal Abstractions in Reinforcement Learning Through Neural Encoding (2016, background): “Understanding a policy modeled by a DNN, either graphically using the state-action diagram or by any other way, is practically impossible; Problems consist of an immense number of states, and policies often rely on skills (Mankowitz et al., 2014), creating more than a single level of planning.”
Multitask Soft Option Learning (2019, background): “ can also severely limit the expressiveness of the ﬁnal policy and lead to suboptimal performance when the temporally extended skills are not able to express the required policy for the task at hand (Mankowitz et al., 2014). Many methods exist for constructing and/or learning skills for particular t”
Using Options and Covariance Testing for Long Horizon Off-Policy Policy Evaluation (2017, background): “Temporal abstraction can reduce the computational complexity of planning and online learning [2, 9, 10, 14].”
Adaptive Skills Adaptive Partitions (ASAP) (2016, methodology): “(Mankowitz et al., 2014; Comanici & Precup, 2010) learn the termination conditions of options.”
Iterative Hierarchical Optimization for Misspecified Problems (IHOMP) (2016, methodology): “Examples include inventory management systems [Mann and Mannor, 2014] as well as maintenance scheduling of generation units and transmission lines in smart grids [Abiri-Jahromi et al., 2013, Wu et al., 2010].”