Michal Nauman

7 papers at tracked venues · 6 at CORE A* · active 2024–2025

DBLP profile ↗ORCID search ↗

Venues

NeurIPS ×3 ICML ×2 AAAI ×1 IJCAI ×1

Frequent coauthors

Marek Cygan

×5

Mateusz Ostaszewski

×3

Aviral Kumar

×3

Pieter Abbeel

×3

Preston Fu

×2

Oleh Rybkin

×2

Sergey Levine

×2

Piotr Milos

×2

Carmelo Sferrazza

×1

Zhiyuan Zhou

×1

Charlie Victor Snell

×1

Krzysztof Jankowski

×1

Papers

A Case for Validation Buffer in Pessimistic Actor-Critic
IJCAI 2025 · Michal Nauman,
Mateusz Ostaszewski
,
Marek Cygan
Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners
NeurIPS 2025 · Michal Nauman,
Marek Cygan
,
Carmelo Sferrazza
,
Aviral Kumar
,
Pieter Abbeel
Compute-Optimal Scaling for Value-Based Deep RL
NeurIPS 2025 ·
Preston Fu
,
Oleh Rybkin
,
Zhiyuan Zhou
, Michal Nauman,
Pieter Abbeel
,
Sergey Levine
,
Aviral Kumar
Decoupled Policy Actor-Critic: Bridging Pessimism and Risk Awareness in Reinforcement Learning
AAAI 2025 · Michal Nauman,
Marek Cygan
Value-Based Deep RL Scales Predictably
ICML 2025 ·
Oleh Rybkin
, Michal Nauman,
Preston Fu
,
Charlie Victor Snell
,
Pieter Abbeel
,
Sergey Levine
,
Aviral Kumar
Bigger, Regularized, Optimistic: scaling for compute and sample efficient continuous control
NeurIPS 2024 · Michal Nauman,
Mateusz Ostaszewski
,
Krzysztof Jankowski
,
Piotr Milos
,
Marek Cygan
Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning
ICML 2024 · Michal Nauman,
Michal Bortkiewicz
,
Piotr Milos
,
Tomasz Trzcinski
,
Mateusz Ostaszewski
,
Marek Cygan