Pre-training with Non-expert Human Demonstration for Deep Reinforcement Learning
This addresses slow learning speeds in deep RL for real-world applications where data is expensive, though it is an incremental improvement.
The paper tackles the data inefficiency of deep reinforcement learning by pre-training on non-expert human demonstrations to improve feature learning, resulting in significant speed improvements in Atari tasks even with noisy data.
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.