Login / Signup
Inverse Reinforcement Learning with Simultaneous Estimation of Rewards and Dynamics.
Michael Herman
Tobias Gindele
Jörg Wagner
Felix Schmitt
Wolfram Burgard
Published in:
AISTATS (2016)
Keyphrases
</>
inverse reinforcement learning
reward function
reinforcement learning
bayesian nonparametric
partially observable environments
preference elicitation
state space
optimal policy
markov decision processes
parameter estimation
dynamical systems
generative model
multi criteria
partially observable