I2RL: online inverse reinforcement learning under occlusion.

Saurabh Arora Prashant Doshi Bikramjit Banerjee

Published in: Auton. Agents Multi Agent Syst. (2021)

Keyphrases

inverse reinforcement learning
reinforcement learning
partially observable environments
bayesian nonparametric
reward function
temporal difference
reinforcement learning algorithms
preference elicitation
multi agent
special case