Paavo Parmas
6 papers · 2018–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π£ Hot Topic Early Bird π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze π Conference Polyglot Β· Bronze πΊοΈ Taxonomy Completionist (12)
π
Keyword Champion
(4)
π
Trend Setter
Venues
Top co-authors
Research topics
Machine Learning
(6)
Optimization & Theory Β· Machine Learning
(5)
Reinforcement Learning
(4)
Methods
(4)
Learning Types Β· Machine Learning
(3)
Deep Learning
(2)
Applications
(1)
Architectures
(1)
Bayesian & Probabilistic
(1)
Learning Types Β· Deep Learning
(1)
Optimization & Theory Β· Deep Learning
(1)
Keywords
likelihood ratio gradient
(4)
reparameterization gradient
(4)
gradient estimation
(3)
policy gradient
(3)
model-based reinforcement learning
(2)
monte carlo estimation
(1)
importance sampling
(1)
message passing
(1)
policy search
(1)
particle filter
(1)
variance reduction
(1)
likelihood ratio
(1)
graphical model
(1)
gradient estimator
(1)
monte carlo estimator
(1)
exploding gradient
(1)
monte carlo gradient
(1)
bisection search
(1)
epigraph form
(1)
lagrangian max-min formulation
(1)
Papers
Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form
ICLR 2025
Model-based Reinforcement Learning with Scalable Composite Policy Gradient Estimators
ICML 2023
Proppo: a Message Passing Framework for Customizable and Composable Learning Algorithms
NeurIPS 2022
A unified view of likelihood ratio and reparameterization gradients
AISTATS 2021
PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos
ICML 2018
Total stochastic gradient algorithms and applications in reinforcement learning
NeurIPS 2018