Logo image
Past Exam Papers
Sign in
Scalable reinforcement learning via actor-model distributed advantage actor-critic
Thesis   Open access

Scalable reinforcement learning via actor-model distributed advantage actor-critic

Pavel Tychler
Master of Science (MSc), University of Johannesburg
2024
Handle:
https://hdl.handle.net/10210/518533

Abstract

Reinforcement learning Distributed artificial intelligence Parallel processing (Electronic computers)
pdf
Tychler_Pavel_MSc_20244.87 MBDownloadView
Open Access

Metrics

2 Record Views

Details

Logo image