Softmax Transformers implement in-context RL through equivalence to weighted softmax TD updates, with error decay under contraction and parameters as global minimizers of pretraining loss.
Proceedings of the International Conference on Machine Learning , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
extension 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
extension 1polarities
extend 1representative citing papers
citing papers explorer
-
Beyond Linear Attention: Softmax Transformers Implement In-Context Reinforcement Learning
Softmax Transformers implement in-context RL through equivalence to weighted softmax TD updates, with error decay under contraction and parameters as global minimizers of pretraining loss.