Minimizing Human Assistance: Augmenting a Single Demonstration for Deep Reinforcement Learning

09/22/2022
by   Abraham George, et al.
6

The use of human demonstrations in reinforcement learning has proven to significantly improve agent performance. However, any requirement for a human to manually 'teach' the model is somewhat antithetical to the goals of reinforcement learning. This paper attempts to minimize human involvement in the learning process while still retaining the performance advantages by using a single human example collected through a simple-to-use virtual reality simulation to assist with RL training. Our method augments a single demonstration to generate numerous human-like demonstrations that, when combined with Deep Deterministic Policy Gradients and Hindsight Experience Replay (DDPG + HER), significantly improve training time on simple tasks and allows the agent to solve a complex task (block stacking) that DDPG + HER alone cannot solve. The model achieves this significant training advantage using a single human example, requiring less than a minute of human input.

READ FULL TEXT

page 2

page 3

page 5

research
07/14/2021

Mixing Human Demonstrations with Self-Exploration in Experience Replay for Deep Reinforcement Learning

We investigate the effect of using human demonstration data in the repla...
research
09/29/2019

Learning from Observations Using a Single Video Demonstration and Human Feedback

In this paper, we present a method for learning from video demonstration...
research
03/29/2023

Learning Complicated Manipulation Skills via Deterministic Policy with Limited Demonstrations

Combined with demonstrations, deep reinforcement learning can efficientl...
research
12/21/2018

Pre-training with Non-expert Human Demonstration for Deep Reinforcement Learning

Deep reinforcement learning (deep RL) has achieved superior performance ...
research
07/07/2020

Guided Exploration with Proximal Policy Optimization using a Single Demonstration

Solving sparse reward tasks through exploration is one of the major chal...
research
11/09/2022

Leveraging Sequentiality in Reinforcement Learning from a Single Demonstration

Deep Reinforcement Learning has been successfully applied to learn robot...
research
12/23/2018

Parallelized Interactive Machine Learning on Autonomous Vehicles

Deep reinforcement learning (deep RL) has achieved superior performance ...

Please sign up or login with your details

Forgot password? Click here to reset