Acme: A research framework for distributed reinforcement learning
Deep reinforcement learning (RL) has led to many recent and groundbreaking advances.
However, these advances have often come at the cost of both increased scale in the …
However, these advances have often come at the cost of both increased scale in the …
Malib: A parallel framework for population-based multi-agent reinforcement learning
Population-based multi-agent reinforcement learning (PB-MARL) encompasses a range of
methods that merge dynamic population selection with multi-agent reinforcement learning …
methods that merge dynamic population selection with multi-agent reinforcement learning …
Toward multicloud access transparency in serverless computing
Towards Multi-cloud Access Transparency in Serverless Computing Page 1 0740-7459 (c)
2020 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission …
2020 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission …
Serverless end game: Disaggregation enabling transparency
For many years, the distributed systems community has struggled to smooth the transition
from local to remote computing. Transparency means concealing the complexities of …
from local to remote computing. Transparency means concealing the complexities of …
[HTML][HTML] Transparent serverless execution of Python multiprocessing applications
Access transparency means that both local and remote resources are accessed using
identical operations. With transparency, unmodified single-machine applications could run …
identical operations. With transparency, unmodified single-machine applications could run …
SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores
The ever-growing complexity of reinforcement learning (RL) tasks demands a distributed
system to efficiently generate and process a massive amount of data. However, existing …
system to efficiently generate and process a massive amount of data. However, existing …
Optimizing communication in deep reinforcement learning with XingTian
Deep Reinforcement Learning (DRL) achieves great success in various domains.
Communication in today's DRL algorithms takes non-negligible time compared to the …
Communication in today's DRL algorithms takes non-negligible time compared to the …
A methodology to build decision analysis tools applied to distributed reinforcement learning
As Artificial Intelligence-based applications become more and more complex, speeding up
the learning phase (which is typically computation-intensive) becomes more and more …
the learning phase (which is typically computation-intensive) becomes more and more …
[PDF][PDF] Research on Transparent Access Technology of Government Big Data
Research on Transparent Access Technology of Government Big Data Page 1 Tehnički
vjesnik 31, 3(2024), 715-725 715 ISSN 1330-3651 (Print), ISSN 1848-6339 (Online) https://doi.org/10.17559/TV-20230630000775 …
vjesnik 31, 3(2024), 715-725 715 ISSN 1330-3651 (Print), ISSN 1848-6339 (Online) https://doi.org/10.17559/TV-20230630000775 …
A hands-on guide to distributed computing paradigms for evolutionary computation
❖ Rui Wang is a Senior Research Scientist at Uber AI. His research interests include
evolutionary algorithms,, complex systems, evolutionary robotics, reinforcement learning …
evolutionary algorithms,, complex systems, evolutionary robotics, reinforcement learning …