# Sample-efficient Deep Reinforcement Learning with Imaginary Rollouts for Human-Robot Interaction

arXiv: https://arxiv.org/abs/1908.05546 · HTML: https://mlsanity.com/paper/1908.05546/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Aug 2019.

## Built on by (most cited first, 3 of 3)

- [MoVEInt: Mixture of Variational Experts for Learning Human-Robot Interactions from Demonstrations](https://mlsanity.com/paper/2407.07636/) (2024)
- [Reinforcement Learning Interventions on Boundedly Rational Human Agents in Frictionful Tasks](https://mlsanity.com/paper/2401.14923/) (2024)
- [Sim-to-Real Deep Reinforcement Learning with Manipulators for Pick-and-place](https://mlsanity.com/paper/2309.09247/) (2023)

## Abstract (arXiv)

Deep reinforcement learning has proven to be a great success in allowing agents to learn complex tasks. However, its application to actual robots can be prohibitively expensive. Furthermore, the unpredictability of human behavior in human-robot interaction tasks can hinder convergence to a good policy. In this paper, we present an architecture that allows agents to learn models of stochastic environments and use them to accelerate learning. We descirbe how an environment model can be learned online and used to generate synthetic transitions, as well as how an agent can leverage these synthetic data to accelerate learning. We validate our approach using an experiment in which a robotic arm has to complete a task composed of a series of actions based on human gestures. Results show that our approach leads to significantly faster learning, requiring much less interaction with the environment. Furthermore, we demonstrate how learned models can be used by a robot to produce optimal plans in real world applications.