Hakutulokset - Cygan, Marek

On Many-Actions Policy Gradient Tekijä Nauman, Michal, Cygan, Marek

Hae kokoteksti
Hae kokoteksti

On the Theory of Risk-Aware Agents: Bridging Actor-Critic and Economics Tekijä Nauman, Michal, Cygan, Marek

Hae kokoteksti
Hae kokoteksti

Debate2Create: Robot Co-design via Multi-Agent LLM Debate Tekijä Qiu, Kevin, Cygan, Marek

Hae kokoteksti
Hae kokoteksti

n-CPS: Generalising Cross Pseudo Supervision to n Networks for Semi-Supervised Semantic Segmentation Tekijä Filipiak, Dominik, Tempczyk, Piotr, Cygan, Marek

Hae kokoteksti
Hae kokoteksti

A Case for Validation Buffer in Pessimistic Actor-Critic Tekijä Nauman, Michal, Ostaszewski, Mateusz, Cygan, Marek

Hae kokoteksti
Hae kokoteksti

Reward-Conditioned Reinforcement Learning Tekijä Nauman, Michal, Cygan, Marek, Abbeel, Pieter

Hae kokoteksti
Hae kokoteksti

Tight Bounds on Subexponential Time Approximation of Set Cover and Related Problems Tekijä Cygan, Marek, Halldórsson, Magnús M., Kortsarz, Guy

Hae kokoteksti
Hae kokoteksti

Vid2Sid: Videos Can Help Close the Sim2Real Gap Tekijä Qiu, Kevin, Zhang, Yu, Cygan, Marek, Hughes, Josie

Hae kokoteksti
Hae kokoteksti

Kine2Go: Kinematic dataset for the Unitree Go2 robot with diverse gaits and motions Tekijä Pałucki, Władysław, Siwak, Paweł, Ciebiera, Krzysztof, Cygan, Marek

Hae kokoteksti
Hae kokoteksti

One Simple Trick to Fix Your Bayesian Neural Network Tekijä Tempczyk, Piotr, Smoczyński, Ksawery, Smolenski-Jensen, Philip, Cygan, Marek

Hae kokoteksti
Hae kokoteksti

Polite Teacher: Semi-Supervised Instance Segmentation with Mutual Learning and Pseudo-Label Thresholding Tekijä Filipiak, Dominik, Zapała, Andrzej, Tempczyk, Piotr, Fensel, Anna, Cygan, Marek

Hae kokoteksti
Hae kokoteksti

Grasping Student: semi-supervised learning for robotic manipulation Tekijä Krzywicki, Piotr, Ciebiera, Krzysztof, Michaluk, Rafał, Maziarz, Inga, Cygan, Marek

Hae kokoteksti
Hae kokoteksti

Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control Tekijä Nauman, Michal, Ostaszewski, Mateusz, Jankowski, Krzysztof, Miłoś, Piotr, Cygan, Marek

Hae kokoteksti
Hae kokoteksti

Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners Tekijä Nauman, Michal, Cygan, Marek, Sferrazza, Carmelo, Kumar, Aviral, Abbeel, Pieter

Hae kokoteksti
Hae kokoteksti

Swim2Real: VLM-Guided System Identification for Sim-to-Real Transfer Tekijä Qiu, Kevin, Walker, Kyle, Michelis, Mike Y., Cygan, Marek, Hughes, Josie

Hae kokoteksti
Hae kokoteksti

Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning Tekijä Nauman, Michal, Bortkiewicz, Michał, Miłoś, Piotr, Trzciński, Tomasz, Ostaszewski, Mateusz, Cygan, Marek

Hae kokoteksti
Hae kokoteksti

RoboMorph: Evolving Robot Morphology using Large Language Models Tekijä Qiu, Kevin, Pałucki, Władysław, Ciebiera, Krzysztof, Fijałkowski, Paweł, Cygan, Marek, Kuciński, Łukasz

Hae kokoteksti
Hae kokoteksti

FlySearch: Exploring how vision-language models explore Tekijä Pardyl, Adam, Matuszek, Dominik, Przebieracz, Mateusz, Cygan, Marek, Zieliński, Bartosz, Wołczyk, Maciej

Hae kokoteksti
Hae kokoteksti

Randomized contractions meet lean decompositions Tekijä Cygan, Marek, Komosa, Paweł, Lokshtanov, Daniel, Pilipczuk, Michał, Pilipczuk, Marcin, Saurabh, Saket, Wahlström, Magnus

Hae kokoteksti
Hae kokoteksti

What Matters in Hierarchical Search for Combinatorial Reasoning Problems? Tekijä Zawalski, Michał, Góral, Gracjan, Tyrolski, Michał, Wiśnios, Emilia, Budrowski, Franciszek, Cygan, Marek, Kuciński, Łukasz, Miłoś, Piotr

Hae kokoteksti
Hae kokoteksti