Learning probabilistic action models from interpretation transitions
Document typeConference report
Rights accessOpen Access
Probabilistic planners are very flexible tools that provide good solutions for difficult tasks. However, they rely on a model of the domain and actions, which they have difficulties to learn for complex tasks. We propose a new learning approach that (a) requires only a set of state transitions to learn the model; (b) can cope with uncertainty in the effects; (c) uses a relational representation to generalize over different objects; and (d) in addition to action effects, it can also learn
CitationMartínez, D., Ribeiro, T., Inoue, K., Alenyà, G., Torras, C. Learning probabilistic action models from interpretation transitions. A: Technical Communications of the International Conference on Logic Programming. "Proceedings of the Technical Communications of the 31st International Conference on Logic Programming (ICLP 2015)". Cork: 2015, p. 1-14.