# Offline to Online Learning for Real-Time Bandwidth Estimation

arXiv: https://arxiv.org/abs/2309.13481 · HTML: https://mlsanity.com/paper/2309.13481/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Offline multi-agent RL, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 8 of its 31 references that are in the map.
- First posted on arXiv 23 Sep 2023.

## Placed in

- Offline RL and imitation learning from data / [Offline multi-agent RL](https://mlsanity.com/offlinerl/offline-multi-agent-rl/)

## Builds on (most cited first, 8 of 8)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Behavioral Cloning from Observation](https://mlsanity.com/paper/1805.01954/) (2018)
- [Implicit Behavioral Cloning](https://mlsanity.com/paper/2109.00137/) (2021)
- [Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization](https://mlsanity.com/paper/1603.00448/) (2016)
- [Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning](https://mlsanity.com/paper/1708.02596/) (2017)
- [Reinforcement learning for bandwidth estimation and congestion control in real-time communications](https://mlsanity.com/paper/1912.02222/) (2019)
- [LSTM-based Video Quality Prediction Accounting for Temporal Distortions in Videoconferencing Calls](https://mlsanity.com/paper/2303.12761/) (2023)

## Built on by (most cited first, 1 of 1)

- [Streetwise Agents: Empowering Offline RL Policies to Outsmart Exogenous Stochastic Disturbances in RTC](https://mlsanity.com/paper/2411.06815/) (2024)

## Abstract (arXiv)

Real-time video applications require accurate bandwidth estimation (BWE) to maintain user experience across varying network conditions. However, increasing network heterogeneity challenges general-purpose BWE algorithms, necessitating solutions that adapt to end-user environments. While widely adopted, heuristic-based methods are difficult to individualize without extensive domain expertise. Conversely, online reinforcement learning (RL) offers ease of customization but neglects prior domain expertise and suffers from sample inefficiency. Thus, we present Merlin, an imitation learning-based solution that replaces the manual parameter tuning of heuristic-based methods with data-driven updates to streamline end-user personalization. Our key insight is that transforming heuristic-based BWE algorithms into neural networks facilitates data-driven personalization. Merlin utilizes Behavioral Cloning to efficiently learn from offline telemetry logs, capturing heuristic policies without live network interactions. The cloned policy can then be seamlessly tailored to end user network conditions through online finetuning. In real intercontinental videoconferencing calls, Merlin matches our heuristic's policy with no statistically significant differences in user quality of experience (QoE). Finetuning Merlin's control policy to end-user environments enables QoE improvements of up to 7.8% compared to the heuristic policy. Lastly, our IL-based design performs competitively with current state-of-the-art online RL techniques but converges with 80% fewer videoconferencing samples, facilitating practical end-user personalization.