RAT reformulates regularized natural policy gradients as vanilla gradients with a transformed advantage, computed efficiently via randomized block Kaczmarz iterations on on-policy data.
International Conference on Machine Learning , pages=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
TRIRL enables explicit dual-ascent IRL via trust-region local policy updates that guarantee monotonic improvement without full RL solves per iteration, outperforming prior imitation methods by 2.4x aggregate IQM and recovering generalizable rewards.
A new adaptive variance estimator for relative sparsity coefficients is introduced that fully utilizes the prior asymptotic normality theorem and incorporates variable selection effects.
citing papers explorer
-
Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation
RAT reformulates regularized natural policy gradients as vanilla gradients with a transformed advantage, computed efficiently via randomized block Kaczmarz iterations on on-policy data.
-
Trust Region Inverse Reinforcement Learning: Explicit Dual Ascent using Local Policy Updates
TRIRL enables explicit dual-ascent IRL via trust-region local policy updates that guarantee monotonic improvement without full RL solves per iteration, outperforming prior imitation methods by 2.4x aggregate IQM and recovering generalizable rewards.
-
An adaptive variance estimator for relative sparsity
A new adaptive variance estimator for relative sparsity coefficients is introduced that fully utilizes the prior asymptotic normality theorem and incorporates variable selection effects.