@inproceedings{SGTlta18,
    author = {Varun Suryan and Nahush Gondhalekar and Pratap Tokekar},
    title = {Multi-Fidelity Model-Free Reinforcement Learning with Gaussian Processes},
    booktitle = {Proceedings of the AAAI Fall Symposium on Reasoning and Learning in Real-World Systems for Long-Term Autonomy},
    pages = {82--87},
    year = {2018},
    abstract = {We study the problem of Reinforcement Learning (RL) using as few real-world samples as possible. A naive application of RL can be inefficient in large and continuous state spaces. We present a Multi-Fidelity Reinforcement Learning (MFRL) model-free algorithm that leverages Gaussian Processes (GPs) to learn the optimal policy in the real world. In the MFRL framework, an agent uses multiple simulators of the real environment to perform actions. With increasing fidelity in a simulator chain, the number of samples used in successively higher simulators can be reduced. By incorporating GPs in the MFRL framework, further reduction in the number of learning samples can be achieved as we move up the simulator chain. We examine the performance of our algorithm through simulations and through real-world experiments for navigation with a ground robot.}
}