PPO (Schulman et al., 2017)

Reported on 6 benchmarks across 2 tasks · 1 paper · 6 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology6 results

Neural Architecture SearchonNATS-Bench Topology, CIFAR-10
Test Accuracy· 2017-07-20
94.02
best: 94.13 (RE (Real et al., 2019))
SOTA
Proximal Policy Optimization Algorithms arXiv:1707.06347
Neural Architecture SearchonNATS-Bench Topology, CIFAR-100
Test Accuracy· 2017-07-20
71.68
SOTA
Proximal Policy Optimization Algorithms arXiv:1707.06347
Neural Architecture SearchonNATS-Bench Topology, ImageNet16-120
Test Accuracy· 2017-07-20
44.95
best: 45.54 (EigenNas (Zhu et al., 2022))
SOTA
Proximal Policy Optimization Algorithms arXiv:1707.06347
AutoMLonNATS-Bench Topology, CIFAR-10
Test Accuracy· 2017-07-20
94.02
best: 94.13 (RE (Real et al., 2019))
SOTA
Proximal Policy Optimization Algorithms arXiv:1707.06347
AutoMLonNATS-Bench Topology, CIFAR-100
Test Accuracy· 2017-07-20
71.68
SOTA
Proximal Policy Optimization Algorithms arXiv:1707.06347
AutoMLonNATS-Bench Topology, ImageNet16-120
Test Accuracy· 2017-07-20
44.95
best: 45.54 (EigenNas (Zhu et al., 2022))
SOTA
Proximal Policy Optimization Algorithms arXiv:1707.06347