Corpus ID: 6398388

Exploration for Multi-task Reinforcement Learning with Deep Generative Models

  title={Exploration for Multi-task Reinforcement Learning with Deep Generative Models},
  author={Sai Praveen Bangaru and J. S. Suhas and Balaraman Ravindran},
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
2 Citations
The Dreaming Variational Autoencoder for Reinforcement Learning Environments
  • 7
  • PDF
Multi-Task Deep Reinforcement Learning for Continuous Action Control
  • 37
  • PDF


Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning
  • 350
  • PDF
Multi-task reinforcement learning: a hierarchical Bayesian approach
  • 233
  • PDF
Control of Memory, Active Perception, and Action in Minecraft
  • 199
  • PDF
Bayesian Multi-Task Reinforcement Learning
  • 87
  • PDF
Value Iteration Networks
  • 402
  • PDF
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
  • 2,946
  • PDF
An Uncertain Future: Forecasting from Static Images Using Variational Autoencoders
  • 377
  • PDF
Auto-Encoding Variational Bayes
  • 11,686
  • PDF
A Practical Guide to Training Restricted Boltzmann Machines
  • 2,444
  • PDF