Corpus ID: 210023753

Information Theoretic Model Predictive Q-Learning

@article{Bhardwaj2020InformationTM,
  title={Information Theoretic Model Predictive Q-Learning},
  author={Mohak Bhardwaj and A. Handa and D. Fox and B. Boots},
  journal={ArXiv},
  year={2020},
  volume={abs/2001.02153}
}

Mohak Bhardwaj, A. Handa, +1 author B. Boots

Published 2020

Computer Science, Mathematics

ArXiv

Model-free Reinforcement Learning (RL) works well when experience can be collected cheaply and model-based RL is effective when system dynamics can be modeled accurately. However, both assumptions can be violated in real world problems such as robotics, where querying the system can be expensive and real-world dynamics can be difficult to model. In contrast to RL, Model Predictive Control (MPC) algorithms use a simulator to optimize a simple policy class online, constructing a closed-loop… CONTINUE READING

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed