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

## TL;DR

This paper enhances deep reinforcement learning efficiency by pre-training neural networks with non-expert human demonstrations, leading to faster learning even with noisy data, demonstrated on Atari games.

## Contribution

It introduces a pre-training method using non-expert demonstrations to improve data efficiency in deep RL, especially in feature learning.

## Key findings

- Significant speed-up in learning with pre-training
- Effective even with noisy and low-quality demonstrations
- Improved data efficiency in Atari domain

## Abstract

Deep reinforcement learning (deep RL) has achieved superior performance in complex sequential tasks by using deep neural networks as function approximators to learn directly from raw input images. However, learning directly from raw images is data inefficient. The agent must learn feature representation of complex states in addition to learning a policy. As a result, deep RL typically suffers from slow learning speeds and often requires a prohibitively large amount of training time and data to reach reasonable performance, making it inapplicable to real-world settings where data is expensive. In this work, we improve data efficiency in deep RL by addressing one of the two learning goals, feature learning. We leverage supervised learning to pre-train on a small set of non-expert human demonstrations and empirically evaluate our approach using the asynchronous advantage actor-critic algorithms (A3C) in the Atari domain. Our results show significant improvements in learning speed, even when the provided demonstration is noisy and of low quality.