Linear self-attention transformers provably implement in-context SARSA and actor-critic via explicit constructions, with gradient flow converging exponentially to the target parameter manifold under rich training MDPs.
and Ba, Jimmy , title =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A specialized PINN architecture solves the spatially inhomogeneous electron Boltzmann equation with high accuracy across gases and electric field strengths without case-specific tuning.
citing papers explorer
-
Transformers Provably Implement In-Context Reinforcement Learning with Policy Improvement
Linear self-attention transformers provably implement in-context SARSA and actor-critic via explicit constructions, with gradient flow converging exponentially to the target parameter manifold under rich training MDPs.
-
A physics-informed neural network approach to solve the spatially inhomogeneous electron Boltzmann equation
A specialized PINN architecture solves the spatially inhomogeneous electron Boltzmann equation with high accuracy across gases and electric field strengths without case-specific tuning.