Learning Abstractions by Transferring Abstract Policies to Grounded State Spaces.

Lawson L. S. Wong

Published in: AAAI Spring Symposia (2018)

Keyphrases

high level
state space
markov chain
learning algorithm
prior knowledge
learning systems
markov decision processes
learning tasks
learning scheme
neural network
decision trees
bayesian networks
multi agent
online learning
unsupervised learning
learning problems