| Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning M Nauman, M Bortkiewicz, M Ostaszewski, P Miłoś, T Trzciński, M Cygan Proceedings of the 41th International Conference on Machine Learning, PMLR, 2024 | 18 | 2024 |
| Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control M Nauman, M Ostaszewski, K Jankowski, P Miłoś, M Cygan NeurIPS 2024 Spotlight, 2024 | 13 | 2024 |
| On the theory of risk-aware agents: Bridging actor-critic and economics M Nauman, M Cygan arXiv preprint arXiv:2310.19527, 2023 | 4 | 2023 |
| Decoupled Actor-Critic M Nauman, M Cygan Aligning Reinforcement Learning Experimentalists and Theorists ICML 2024, 2024 | 3 | 2024 |
| Seeing through their eyes: Evaluating visual perspective taking in vision language models G Góral, A Ziarko, M Nauman, M Wołczyk arXiv preprint arXiv:2409.12969, 2024 | 1 | 2024 |
| Value-Based Deep RL Scales Predictably O Rybkin, M Nauman, P Fu, C Snell, P Abbeel, S Levine, A Kumar arXiv preprint arXiv:2502.04327, 2025 | | 2025 |
| A Case for Validation Buffer in Pessimistic Actor-Critic M Nauman, M Ostaszewski, M Cygan Aligning Reinforcement Learning Experimentalists and Theorists ICML 2024, 2024 | | 2024 |
| On Many-Actions Policy Gradient M Nauman, M Cygan Proceedings of the 40th International Conference on Machine Learning, PMLR …, 2023 | | 2023 |
Marek CyganUniversity of WarsawDirección de correo verificada de mimuw.edu.pl