Transformers are Meta-Reinforcement Learners
Paper
•
2206.06614
•
Published
Luckeciano Carvalho Melo
luckeciano
·
AI & ML interests
Reinforcement Learning
Recent Activity
published
a model
about 1 month ago
luckeciano/Llama-3.1-8B-Instruct-CAPO-Base-v2-FisherMaskToken-1e-10-HessianMaskToken-0.0-LR-7.5e-7_2916
published
a model
about 1 month ago
luckeciano/Llama-3.1-8B-Instruct-CAPO-Base-v2-FisherMaskToken-1e-9-HessianMaskToken-0.0-LR-7.5e-7_9573
published
a model
about 1 month ago
luckeciano/Llama-3.1-8B-Instruct-CAPO-Base-v2-FisherMaskToken-1e-8-HessianMaskToken-0.0-LR-7.5e-7_8245
Organizations
authored
a
paper
about 2 years ago