Skip to content
conftrace_

Michal Nauman

5 papers · 2023–2025 · 3 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 ↓
🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze

Venues

ICML (3) AAAI (1) NeurIPS (1)

Top co-authors

Marek Cygan (4) Piotr Miłoś (2) Mateusz Ostaszewski (2) Tomasz Trzcinski (1) Michał Bortkiewicz (1) Krzysztof Jankowski (1) Pieter Abbeel (1) Charlie Victor Snell (1) Aviral Kumar (1) Preston Fu (1)

Research topics

Reinforcement Learning (4) Methods (4) Machine Learning (2) Applications (2) Artificial Intelligence (1) Application Areas (1) Core AI (1) Learning Types (1) Optimization & Theory (1)

Keywords

sample efficiency (2) regularization (1) policy gradient (1) continuous control (1) model-based reinforcement learning (1) variance reduction (1) expected utility (1) optimistic exploration (1) plasticity loss (1) soft actor-critic (1) deep rl (1) continuous action (1) pareto frontier (1) model-free algorithm (1) pessimistic policy (1) risk-aware reinforcement learning (1) overfitting (1) hyperparameters (1) overestimation (1) off-policy (1)

Papers

Decoupled Policy Actor-Critic: Bridging Pessimism and Risk Awareness in Reinforcement Learning AAAI 2025 Value-Based Deep RL Scales Predictably ICML 2025 Bigger, Regularized, Optimistic: scaling for compute and sample efficient continuous control NeurIPS 2024 Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning ICML 2024 On Many-Actions Policy Gradient ICML 2023