PISTO augments stochastic trajectory optimization with proximal KL regularization, yielding closed-form mean updates via importance sampling that outperform STOMP, CHOMP, CEM, and MPPI on robot arm and MuJoCo benchmarks.
A generalized path integral control approach to reinforce- ment learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PISTO: Proximal Inference for Stochastic Trajectory Optimization
PISTO augments stochastic trajectory optimization with proximal KL regularization, yielding closed-form mean updates via importance sampling that outperform STOMP, CHOMP, CEM, and MPPI on robot arm and MuJoCo benchmarks.