# Comyco: Quality-Aware Adaptive Video Streaming via Imitation Learning

## TL;DR

Comyco is a novel quality-aware adaptive video streaming method that leverages imitation learning to improve sample efficiency and video quality, outperforming existing approaches in both efficiency and quality metrics.

## Contribution

It introduces a new imitation learning-based ABR approach that incorporates video quality awareness and expert trajectory imitation to enhance learning efficiency and streaming quality.

## Key findings

- Significantly reduces sample requirements by 1700x.
- Achieves 16x faster training times compared to prior methods.
- Improves average QoE by up to 16.79% over existing approaches.

## Abstract

Learning-based Adaptive Bit Rate~(ABR) method, aiming to learn outstanding strategies without any presumptions, has become one of the research hotspots for adaptive streaming. However, it typically suffers from several issues, i.e., low sample efficiency and lack of awareness of the video quality information. In this paper, we propose Comyco, a video quality-aware ABR approach that enormously improves the learning-based methods by tackling the above issues. Comyco trains the policy via imitating expert trajectories given by the instant solver, which can not only avoid redundant exploration but also make better use of the collected samples. Meanwhile, Comyco attempts to pick the chunk with higher perceptual video qualities rather than video bitrates. To achieve this, we construct Comyco's neural network architecture, video datasets and QoE metrics with video quality features. Using trace-driven and real-world experiments, we demonstrate significant improvements of Comyco's sample efficiency in comparison to prior work, with 1700x improvements in terms of the number of samples required and 16x improvements on training time required. Moreover, results illustrate that Comyco outperforms previously proposed methods, with the improvements on average QoE of 7.5% - 16.79%. Especially, Comyco also surpasses state-of-the-art approach Pensieve by 7.37% on average video quality under the same rebuffering time.