Universal Option Models

32 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.

Successor Features for Transfer in Reinforcement Learning (2016, background): “[28], whose universal option model closely resembles our approach in some aspects (the main difference being that they do not do GPI).”
Deep Successor Reinforcement Learning (2016, methodology): “nt improvements over -greedy, but are limited due to the underlying models functioning at the level of basic actions. Hierarchical reinforcement learning algorithms [1] such as the options framework [38, 39] provide a ﬂexible framework to create temporal abstractions, which will enable exploration a”
Symmetry Learning for Function Approximation in Reinforcement Learning (2017, methodology): “ss by learning from agent observations but their approach is suboptimal as they fail to discover all the abstractions [12]. 2 Recent approaches for incorporating TAA use linear function approximation [17, 18] and have been shown to be eective. Value function generalization for sub goal setting by [1”
Universal Value Function Approximators (2015, methodology): “Finally, a UVFA could also be used as a universal option model (Yao et al., 2014).”