Model-Based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs
Abstract
We present two elegant solutions for modeling continuous-time dynamics, in a novel model-based reinforcement learning (RL) framework for semi-Markov decision processes (SMDPs), using neural ordinary differential equations (ODEs). Our models accurately characterize continuous-time dynamics and enable us to develop high-performing policies using a small amount of data. We also develop a model-based approach for optimizing time schedules to reduce interaction rates with the environment while maintaining the near-optimal performance, which is not possible for model-free methods. We experimentally demonstrate the efficacy of our methods across various continuous-time domains.
Cite
Text
Du et al. "Model-Based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs." Neural Information Processing Systems, 2020.Markdown
[Du et al. "Model-Based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs." Neural Information Processing Systems, 2020.](https://mlanthology.org/neurips/2020/du2020neurips-modelbased/)BibTeX
@inproceedings{du2020neurips-modelbased,
title = {{Model-Based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs}},
author = {Du, Jianzhun and Futoma, Joseph and Doshi-Velez, Finale},
booktitle = {Neural Information Processing Systems},
year = {2020},
url = {https://mlanthology.org/neurips/2020/du2020neurips-modelbased/}
}