Deep Inverse Q-learning with Constraints.

Gabriel Kalweit Maria Hügle Moritz Werling Joschka Boedecker

Published in: NeurIPS (2020)

Keyphrases

reinforcement learning
multi agent
state space
cooperative
learning algorithm
global constraints
function approximation
constraint programming
deep learning
neural network
model free
constrained optimization
constraint satisfaction
dynamic environments
sufficient conditions
co occurrence
case study