Prati
£ukasz Kuciński
£ukasz Kuciński
Polish Academy of Sciences; University of Warsaw; IDEAS NCBR
Potvršena adresa e-po¹te na impan.pl - Početna stranica
Naslov
Citirano
Citirano
Godina
Continual World: A Robotic Benchmark For Continual Reinforcement Learning
M Wo³czyk, M Zaj±c, R Pascanu, £ Kuciński, P Mi³o¶
NeurIPS 2021, arXiv preprint arXiv:2105.10919, 2021
622021
Complete discounted cash flow valuation
L Gajek, £ Kuciński
Insurance: Mathematics and Economics 73, 1-19, 2017
292017
Subgoal Search For Complex Reasoning Tasks
K Czechowski, T Odrzygó¼d¼, M Zbysiński, M Zawalski, K Olejnik, Y Wu, ...
NeurIPS 2021, arXiv preprint arXiv:2108.11204, 2021
262021
Disentangling Transfer in Continual Reinforcement Learning
M Wo³czyk, M Zaj±c, R Pascanu, £ Kuciński, P Mi³o¶
NeurIPS 2022, arXiv preprint arXiv:2209.13900, 2022
202022
Magnushammer: A transformer-based approach to premise selection
M Miku³a, S Antoniak, S Tworkowski, AQ Jiang, JP Zhou, C Szegedy, ...
arXiv preprint arXiv:2303.04488, 2023
172023
Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication
£ Kuciński, T Korbak, P Ko³odziej, P Mi³o¶
NeurIPS 2021, 2021
142021
Continuous control with ensemble deep deterministic policy gradients
P Januszewski, M Olko, M Królikowski, J ¦wi±tkowski, M Andrychowicz, ...
NeurIPS Deep RL workshop 2021, arXiv preprint arXiv:2111.15382, 2021
82021
Uncertainty-sensitive learning and planning with ensembles
P Mi³o¶, £ Kuciński, K Czechowski, P Kozakowski, M Klimek
Uncertainty and Robustness in Deep Learning Workshop, ICML 2020, arXiv …, 2019
82019
Interaction history as a source of compositionality in emergent communication
T Korbak, J Zubek, £ Kuciński, P Mi³o¶, J R±czaszek-Leonardi
Interaction Studies 22 (2), 212-243, 2021
72021
Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search
M Zawalski, M Tyrolski, K Czechowski, D Stachura, P Piźkos, ...
ICLR 2023, arXiv preprint arXiv:2206.00702, 2022
62022
Developmentally motivated emergence of compositional communication via template transfer
T Korbak, J Zubek, £ Kuciński, P Mi³o¶, J R±czaszek-Leonardi
arXiv preprint arXiv:1910.06079, 2019
62019
Emergence of compositional language in communication through noisy channel
£ Kuciński, P Ko³odziej, P Mi³o¶
Language in Reinforcement Learning Workshop at ICML 2020, 2020
42020
Structure and Randomness in Planning and Reinforcement Learning
K Czechowski, P Januszewski, P Kozakowski, £ Kuciński, P Mi³o¶
2021 International Joint Conference on Neural Networks (IJCNN), 1-8, 2021
22021
To value a firm using DCF you must know its value: how to cope with this paradox
L Gajek, £ Kuciński
Manuscript, 2012
22012
Optimal risk sharing as a cooperative game
£ Kuciński
Applicationes Mathematicae 2 (38), 219-242, 2011
22011
The Role of Forgetting in Fine-Tuning Reinforcement Learning Models
M Wolczyk, B Cupia³, M Ostaszewski, M Bortkiewicz, M Zaj±c, R Pascanu, ...
12023
: Stochastic Time Series Modeling With Transformer
£ Kuciński, W Drzewakowski, M Olko, P Kozakowski, £ Maziarka, ...
arXiv preprint arXiv:2403.05713, 2024
2024
GUIDE: Guidance-based Incremental Learning with Diffusion Models
B Cywiński, K Deja, T Trzciński, B Twardowski, £ Kuciński
arXiv preprint arXiv:2403.03938, 2024
2024
Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem
M Wo³czyk, B Cupia³, M Ostaszewski, M Bortkiewicz, M Zaj±c, R Pascanu, ...
arXiv preprint arXiv:2402.02868, 2024
2024
Structured Packing in LLM Training Improves Long Context Utilization
K Staniszewski, S Tworkowski, S Jaszczur, H Michalewski, £ Kuciński, ...
arXiv preprint arXiv:2312.17296, 2023
2023
Sustav trenutno ne mo¾e provesti ovu radnju. Poku¹ajte ponovo kasnije.
Članci 1–20