AI agents trained through competitive debate can allow polynomial-time human judges to oversee PSPACE-level questions, with MNIST experiments boosting sparse classifier accuracy from 59% to 89% using only 6 pixels.
Efficient selectivity and backup operators in monte-carlo tree search
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2018 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AI safety via debate
AI agents trained through competitive debate can allow polynomial-time human judges to oversee PSPACE-level questions, with MNIST experiments boosting sparse classifier accuracy from 59% to 89% using only 6 pixels.