no code implementations • 1 Mar 2024 • Michal Nauman, Mateusz Ostaszewski, Marek Cygan
VPL uses a small validation buffer to adjust the levels of pessimism throughout the agent training, with the pessimism set such that the approximation error of the critic targets is minimized.
no code implementations • 1 Mar 2024 • Michal Nauman, Michał Bortkiewicz, Mateusz Ostaszewski, Piotr Miłoś, Tomasz Trzciński, Marek Cygan
We tested these agents across 14 diverse tasks from 2 simulation benchmarks.
1 code implementation • 12 Feb 2024 • Jakub Krajewski, Jan Ludziejewski, Kamil Adamczewski, Maciej Pióro, Michał Krutul, Szymon Antoniak, Kamil Ciebiera, Krystian Król, Tomasz Odrzygóźdź, Piotr Sankowski, Marek Cygan, Sebastian Jaszczur
Our findings not only show that MoE models consistently outperform dense Transformers but also highlight that the efficiency gap between dense and MoE models widens as we scale up the model size and training budget.
1 code implementation • 8 Jan 2024 • Maciej Pióro, Kamil Ciebiera, Krystian Król, Jan Ludziejewski, Michał Krutul, Jakub Krajewski, Szymon Antoniak, Piotr Miłoś, Marek Cygan, Sebastian Jaszczur
State Space Models (SSMs) have become serious contenders in the field of sequential modeling, challenging the dominance of Transformers.
no code implementations • 30 Oct 2023 • Michal Nauman, Marek Cygan
Risk-aware Reinforcement Learning (RL) algorithms like SAC and TD3 were shown empirically to outperform their risk-neutral counterparts in a variety of continuous-action tasks.
1 code implementation • 24 Oct 2023 • Szymon Antoniak, Sebastian Jaszczur, Michał Krutul, Maciej Pióro, Jakub Krajewski, Jan Ludziejewski, Tomasz Odrzygóźdź, Marek Cygan
The operation of matching experts and tokens is discrete, which makes MoE models prone to issues like training instability and uneven expert utilization.
1 code implementation • 8 Mar 2023 • Piotr Krzywicki, Krzysztof Ciebiera, Rafał Michaluk, Inga Maziarz, Marek Cygan
Gathering real-world data from the robot quickly becomes a bottleneck when constructing a robot learning system for grasping.
no code implementations • 7 Nov 2022 • Dominik Filipiak, Andrzej Zapała, Piotr Tempczyk, Anna Fensel, Marek Cygan
We present Polite Teacher, a simple yet effective method for the task of semi-supervised instance segmentation.
1 code implementation • 24 Oct 2022 • Michal Nauman, Marek Cygan
We study the variance of stochastic policy gradients (SPGs) with many action samples per state.
no code implementations • 26 Jul 2022 • Piotr Tempczyk, Ksawery Smoczyński, Philip Smolenski-Jensen, Marek Cygan
One of the most popular estimation methods in Bayesian neural networks (BNN) is mean-field variational inference (MFVI).
no code implementations • 14 Dec 2021 • Dominik Filipiak, Piotr Tempczyk, Marek Cygan
We present n-CPS - a generalisation of the recent state-of-the-art cross pseudo supervision (CPS) approach for the task of semi-supervised semantic segmentation.
no code implementations • 16 Feb 2018 • Maciej Jaśkowski, Jakub Świątkowski, Michał Zając, Maciej Klimek, Jarek Potiuk, Piotr Rybicki, Piotr Polatowski, Przemysław Walczyk, Kacper Nowicki, Marek Cygan
In this work we improve on one of the most promising approaches, the Grasp Quality Convolutional Neural Network (GQ-CNN) trained on the DexNet 2. 0 dataset.
no code implementations • 26 Jul 2016 • Marek Cygan, Łukasz Kowalik, Arkadiusz Socała, Krzysztof Sornat
Motivated by this, we then show a parameterized approximation scheme, running in time $\mathcal{O}^\star(\left({3}/{\epsilon}\right)^{2d})$, which is essentially tight assuming ETH.
1 code implementation • 7 Nov 2012 • Hans L. Bodlaender, Marek Cygan, Stefan Kratsch, Jesper Nederlof
It is well known that many local graph problems, like Vertex Cover and Dominating Set, can be solved in 2^{O(tw)}|V|^{O(1)} time for graphs G=(V, E) with a given tree decomposition of width tw.
Data Structures and Algorithms Computational Complexity Discrete Mathematics F.2.2; G.2.8