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

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.

References in corpus (8)

• Continuous control with deep reinforcement learning
• Asynchronous Methods for Deep Reinforcement Learning
• The Arcade Learning Environment: An Evaluation Platform for General Agents
• Benchmarking Deep Reinforcement Learning for Continuous Control
• Reinforcement Learning with Unsupervised Auxiliary Tasks
• Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning
• Augmenting Supervised Neural Networks with Unsupervised Objectives for Large-scale Image Classification
• Deep Reinforcement Learning for Doom using Unsupervised Auxiliary Tasks

Cited by in corpus (1)

• A novel policy for pre-trained Deep Reinforcement Learning for Speech Emotion Recognition