Learning When to Trust a Dynamics Model for Planning in Reduced State Spaces.

Dale McConachie Thomas Power Peter Mitrano Dmitry Berenson

Published in: CoRR (2020)

Keyphrases

computational model
learning scheme
learning algorithm
probabilistic model
high level
prior knowledge
reinforcement learning
decision trees
online learning
machine learning
decision theoretic
learning models
learning phase
trust model
planning problems
domain independent
experimental data
mathematical model