Paavo Parmas

14 papers A* 5A 2Journal 7
YearRankTypeTitle / Venue / Authors
2025 J jnl
Double Horizon Model-Based Policy Optimization.
CoRR
Akihiro Kubo, Paavo Parmas, Shin Ishii
2025 J jnl
Double Horizon Model-Based Policy Optimization.
Trans. Mach. Learn. Res.
Akihiro Kubo, Paavo Parmas, Shin Ishii
2025 A* conf
Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form.
ICLR
Toshinori Kitamura, Tadashi Kozuno, Wataru Kumagai, Kenta Hoshino, Yohei Hosoe, Kazumi Kasaura, Masashi Hamaya, Paavo Parmas, Yutaka Matsuo
2024 J jnl
Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form.
CoRR
Toshinori Kitamura, Tadashi Kozuno, Wataru Kumagai, Kenta Hoshino, Yohei Hosoe, Kazumi Kasaura, Masashi Hamaya, Paavo Parmas, Yutaka Matsuo
2023 A* conf
Model-based Reinforcement Learning with Scalable Composite Policy Gradient Estimators.
ICML
Paavo Parmas, Takuma Seno, Yuma Aoki
2022 A* conf
Proppo: a Message Passing Framework for Customizable and Composable Learning Algorithms.
NeurIPS
Paavo Parmas, Takuma Seno
2021 A conf
A unified view of likelihood ratio and reparameterization gradients.
AISTATS
Paavo Parmas, Masashi Sugiyama
2021 J jnl
A unified view of likelihood ratio and reparameterization gradients.
CoRR
Paavo Parmas, Masashi Sugiyama
2020 A conf
Neural Replicator Dynamics: Multiagent Learning via Hedging Policy Gradients.
AAMAS
Daniel Hennes, Dustin Morrill, Shayegan Omidshafiei, Rémi Munos, Julien Pérolat, Marc Lanctot, Audrunas Gruslys, Jean-Baptiste Lespiau, Paavo Parmas, Edgar A. Duéñez-Guzmán, Karl Tuyls
2019 J jnl
A unified view of likelihood ratio and reparameterization gradients and an optimal importance sampling scheme.
CoRR
Paavo Parmas, Masashi Sugiyama
2019 J jnl
PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos.
CoRR
Paavo Parmas, Carl Edward Rasmussen, Jan Peters, Kenji Doya
2019 J jnl
Total stochastic gradient algorithms and applications in reinforcement learning.
CoRR
Paavo Parmas
2018 A* conf
PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos.
ICML
Paavo Parmas, Carl Edward Rasmussen, Jan Peters, Kenji Doya
2018 A* conf
Total stochastic gradient algorithms and applications in reinforcement learning.
NeurIPS
Paavo Parmas