Nitro: Boosting Distributed Reinforcement Learning with Serverless Computing

H Yu, J Carter, H Wang, D Tiwari, J Li… - Proceedings of the VLDB …, 2024 - dl.acm.org
Deep reinforcement learning (DRL) has demonstrated significant potential in various
applications, including gaming AI, robotics, and system scheduling. DRL algorithms …

[PDF][PDF] Towards Latency Efficient DRL Inference: Improving UAV Obstacle Avoidance at the Edge Through Model Compression

P McEnroe, S Wang, M Liyanage - 2024 IEEE 27th International …, 2024 - researchgate.net
It is vital that autonomous Unmanned Aerial Vehicles (UAVs) are able to avoid obstacles
effectively. When avoiding such obstacles it is important that movement decision are made …

High-throughput Sampling, Communicating and Training for Reinforcement Learning Systems

L Zhao, X Dai, Z Zhao, Y **n, Y Hu… - 2023 IEEE/ACM 31st …, 2023 - ieeexplore.ieee.org
Reinforcement Learning (RL) algorithms require large amounts of computational resources
and time to train due to the simultaneous model training and real-time interactions with …