Next Article in Journal
Crowdsensing for Characterizing Mobility and Its Impact on the Subjective Wellbeing in an Underdeveloped Region
Previous Article in Journal
Development and Assist-As-Needed Control of an End-Effector Upper Limb Rehabilitation Robot
Previous Article in Special Issue
Comparing Deep Learning and Statistical Methods in Forecasting Crowd Distribution from Aggregated Mobile Phone Data
Article

World-Models for Bitrate Streaming

Computer Laboratory, University of Cambridge, Cambridge CB3 0FD, UK
*
Author to whom correspondence should be addressed.
Appl. Sci. 2020, 10(19), 6685; https://doi.org/10.3390/app10196685
Received: 18 August 2020 / Revised: 17 September 2020 / Accepted: 18 September 2020 / Published: 24 September 2020
(This article belongs to the Special Issue AI in Mobile Networks)
Adaptive bitrate (ABR) algorithms optimize the quality of streaming experiences for users in client-side video players, especially in unreliable or slow mobile networks. Several rule-based heuristic algorithms can achieve stable performance, but they sometimes fail to properly adapt to changing network conditions. Fluctuating bandwidth may cause algorithms to default to behavior that creates a negative experience for the user. ABR algorithms can be generated with reinforcement learning, a decision-making paradigm in which an agent learns to make optimal choices through interactions with an environment. Training reinforcement learning algorithms for bitrate streaming requires building a simulator for an agent to experience interactions quickly; training an agent in the real environment is infeasible due to the long step times in real environments. This project explores using supervised learning to construct a world-model, or a learned simulator, from recorded interactions. A reinforcement learning agent that is trained inside of the learned model, rather than a simulator, can outperform rule-based heuristics. Furthermore, agents that are trained inside the learned world-model can outperform model-free agents in low sample regimes. This work highlights the potential for world-models to quickly learn simulators, and to be used for generating optimal policies. View Full-Text
Keywords: reinforcement learning; bitrate streaming; world-models; video streaming; model-based reinforcement learning reinforcement learning; bitrate streaming; world-models; video streaming; model-based reinforcement learning
Show Figures

Figure 1

MDPI and ACS Style

Brown, H.; Fricke, K.; Yoneki, E. World-Models for Bitrate Streaming. Appl. Sci. 2020, 10, 6685. https://doi.org/10.3390/app10196685

AMA Style

Brown H, Fricke K, Yoneki E. World-Models for Bitrate Streaming. Applied Sciences. 2020; 10(19):6685. https://doi.org/10.3390/app10196685

Chicago/Turabian Style

Brown, Harrison, Kai Fricke, and Eiko Yoneki. 2020. "World-Models for Bitrate Streaming" Applied Sciences 10, no. 19: 6685. https://doi.org/10.3390/app10196685

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop