Corpus ID: 6398388

Exploration for Multi-task Reinforcement Learning with Deep Generative Models

@article{Bangaru2016ExplorationFM,
  title={Exploration for Multi-task Reinforcement Learning with Deep Generative Models},
  author={Sai Praveen Bangaru and J. S. Suhas and Balaraman Ravindran},
  journal={ArXiv},
  year={2016},
  volume={abs/1611.09894}
}

• Sai Praveen Bangaru, J. S. Suhas, Balaraman Ravindran
• Published 2016
• Computer Science
• ArXiv

Exploration in multi-task reinforcement learning is critical in training agents to deduce the underlying MDP. Many of the existing exploration frameworks such as $E^3$, $R_{max}$, Thompson sampling assume a single stationary MDP and are not suitable for system identification in the multi-task setting. We present a novel method to facilitate exploration in multi-task reinforcement learning using deep generative models. We supplement our method with a low dimensional energy model to learn the… Expand

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed