Sign in
Inverse reinforcement learning with leveraged Gaussian processes.
Kyungjae Lee
Sungjoon Choi
Songhwai Oh
Published in:
IROS (2016)
Keyphrases
</>
gaussian processes
inverse reinforcement learning
preference elicitation
gaussian process
gaussian process regression
reward function
temporal difference
multi task learning
hyperparameters
multi task
dirichlet process
reinforcement learning
dynamic programming
probabilistic model
closed form
multi criteria