Action-model acquisition for planning via transfer learning

96 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.

Federated Deep Reinforcement Learning (2019, unknown): “In the future, it would be interesting to study more members in the federation with background knowledge represented by (probably incomplete) action models (Zhuo et al., 2014; Zhuo & Yang, 2014; Zhuo & Kambham-pati, 2017).”
Robust planning with incomplete domain models (2017, background): “Similarly, although there exist efforts (Amir and Chang, 2008; Yang et al., 2007; Zhuo and Yang, 2014; Cresswell et al., 2013) that attempt to either learn models from scratch or revise existing ones, their operation is contingent on the availability of successful plan traces or access to execution ”
A review of learning planning action models (2018, methodology): “…problem can be stated as: given a collection C of m clauses ( C 1 , ..., C m ) involving the disjunction of n logical variables, with clause weights w i , ﬁnd a truth assignment of the logical variables that maximizes the total weight of the satisﬁed clauses in C (Zhuo & Yang (2014)).”