A latent Q-Barrier shield learns context, dynamics, and cost critic to enforce safety constraints at action level in in-context RL, with a conditional barrier-margin guarantee and benchmark gains.
Amago-2: Breaking the multi-task barrier in meta-reinforcement learning with transformers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Latent Q-Barrier Shielding for Safe In-Context Reinforcement Learning
A latent Q-Barrier shield learns context, dynamics, and cost critic to enforce safety constraints at action level in in-context RL, with a conditional barrier-margin guarantee and benchmark gains.