Delightful Policy Gradient removes exponential corner trapping in softmax policy optimization for bandits and tabular MDPs, achieving logarithmic escape times and global O(1/t) convergence.
Advances in Neural Information Processing Systems , volume=
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
-
Delightful Gradients Accelerate Corner Escape
Delightful Policy Gradient removes exponential corner trapping in softmax policy optimization for bandits and tabular MDPs, achieving logarithmic escape times and global O(1/t) convergence.