Dynamics-Aware Comparison of Learned Reward Functions.

Blake Wulfe Logan Michael Ellis Jean Mercat Rowan Thomas McAllister Adrien Gaidon

Published in: ICLR (2022)

Keyphrases

reward function
multiple agents
markov decision processes
dynamical systems
transition probabilities
markov decision process
social networks
bayesian networks
objective function
prior knowledge
hidden markov models
state space
markov chain
inverse reinforcement learning