Spatiotemporal Costmap Inference for MPC via Deep Inverse Reinforcement Learning.
Keuntaek LeeDavid IseleEvangelos A. TheodorouSangjae BaePublished in: CoRR (2022)
Keyphrases
- inverse reinforcement learning
- bayesian nonparametric
- partially observable environments
- preference elicitation
- bayesian networks
- probabilistic inference
- mixture model
- reward function
- supervised learning
- utility function
- control system
- hidden markov models
- game theory
- belief networks
- exact inference
- control policies