Regularizing Neural Networks for Future Trajectory Prediction via Inverse Reinforcement Learning.

Dooseop Choi Kyoungwook Min Jeongdan Choi

Published in: CoRR (2019)

Keyphrases

inverse reinforcement learning
neural network
bayesian nonparametric
preference elicitation
partially observable environments
artificial neural networks
fuzzy logic
em algorithm
reward function
genetic algorithm
reinforcement learning
learning tasks