Concurrent Hierarchical Reinforcement Learning

By Bhaskara Marthi. 2005

109 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

Learning World Graphs to Accelerate Hierarchical Reinforcement Learning (2019, positive): “Therefore, in the next stage, we propose a hierarchical reinforcement learning [54, 63] (HRL) approach to incorporate the world graph for solving speciﬁc downstream tasks.”
Modular Multitask Reinforcement Learning with Policy Sketches (2016, methodology): “Like our approach, HAMs begin with a representation of a high-level policy as an automaton (or a more general computer program; Andre & Russell, 2001; Marthi et al., 2004) and use reinforcement learning to ﬁll in low-level details.”
A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning (2010, methodology): “Even if this difficulty is surmounted, as evidenced by the last line in the concluding remarks of [Marthi et al., 2005], there is an imperative need for designing faster algorithms in HRL.”
Rationality and Intelligence: A Brief Update (2013, background): “The theory can be applied to agent architectures defined by arbitrarypartial programs—that is, agent programs in which the choice of action at any point may be left unspecifid Andre and Russell (2002); Marthi et al (2005).”
A Survey of Real-Time Strategy Game AI Research and Competition in StarCraft (2013, unknown): “A few approaches, like CAT [18], Darmok [64], or ALisp [53], try to deal with the problem in a monolithic manner, by using a single AI technique.”
Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration (2018, result): “In contrast to previous instantiations of the HAM framework (Andre, 2003; Marthi & Guestrin, 2005), which require programmers to specify these constraints manually, our work automatically induces constraints from user demonstrations, which do not require special skills to provide.”
A Bayesian model for RTS units control applied to StarCraft (2011, background): “However, adaptivity of behavior by parameters learning is not the main focus of these models, and unit control is a task that would require a huge amount of hand tuning of the behaviors to be really efﬁcient.”
Hierarchical Approaches (2012, unknown): “Marthi et al (2005) extend partial programs (Section 2.3) to the concurrent action case using multi-threaded concurrentALisp.”
A Review of Real-Time Strategy Game AI (2014, background): “Marthi et al. (2005) argues that it is preferable to decrease the apparent complexity of RTS games and potentially increase the effectiveness of RL or other techniques by decomposing the game into a hierarchy of interacting parts.”