Login / Signup
Towards Resolving Unidentifiability in Inverse Reinforcement Learning.
Kareem Amin
Satinder P. Singh
Published in:
CoRR (2016)
Keyphrases
</>
inverse reinforcement learning
bayesian nonparametric
partially observable environments
preference elicitation
reward function
temporal difference
dynamic programming
decision makers
random variables
evaluation function
multi criteria