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.
Thirty-seventh Conference on Neural Information Processing Systems , year =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
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.