ATLAS uses active learning with disentangled RNN ensembles to design experiments that recover RL agent models from bandit behavior 5-10x more efficiently than random or expert baselines in simulations.
Treloar, Nathan Braniff, Brian Ingalls, and Chris P
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
-
ATLAS: Active Theory Learning for Automated Science
ATLAS uses active learning with disentangled RNN ensembles to design experiments that recover RL agent models from bandit behavior 5-10x more efficiently than random or expert baselines in simulations.