Search Results - "Kurin, Vitaly"

Towards a Principled Integration of Multi-camera Re-identification and Tracking Through Optimal Bayes Filters by Beyer, Lucas, Breuers, Stefan, Kurin, Vitaly, Leibe, Bastian

“…With the rise of end-to-end learning through deep learning, person detectors and re-identification (ReID) models have recently become very strong. Multi-target…”
Get full text

Learning From Demonstration in the Wild by Behbahani, Feryal, Shiarlis, Kyriacos, Chen, Xi, Kurin, Vitaly, Kasewa, Sudhanshu, Stirbu, Ciprian, Gomes, Joao, Paul, Supratik, Oliehoek, Frans A., Messias, Joao, Whiteson, Shimon

“…Learning from demonstration (LfD) is useful in settings where hand-coding behaviour or a reward function is impractical. It has succeeded in a wide range of…”
Get full text

Deep Coordination Graphs by Böhmer, Wendelin, Kurin, Vitaly, Whiteson, Shimon

“…This paper introduces the deep coordination graph (DCG) for collaborative multi-agent reinforcement learning. DCG strikes a flexible trade-off between…”
Get full text

Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezing by Blake, Charlie, Kurin, Vitaly, Igl, Maximilian, Whiteson, Shimon

“…Recent research has shown that graph neural networks (GNNs) can learn policies for locomotion control that are as effective as a typical multi-layer perceptron…”
Get full text

Fast Efficient Hyperparameter Tuning for Policy Gradients by Paul, Supratik, Kurin, Vitaly, Whiteson, Shimon

“…The performance of policy gradient methods is sensitive to hyperparameter settings that must be tuned for any new application. Widely used grid search methods…”
Get full text

My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control by Kurin, Vitaly, Igl, Maximilian, Rocktäschel, Tim, Boehmer, Wendelin, Whiteson, Shimon

“…Multitask Reinforcement Learning is a promising way to obtain models with better performance, generalisation, data efficiency, and robustness. Most existing…”
Get full text

You May Not Need Ratio Clipping in PPO by Sun, Mingfei, Kurin, Vitaly, Liu, Guoqing, Devlin, Sam, Qin, Tao, Hofmann, Katja, Whiteson, Shimon

“…Proximal Policy Optimization (PPO) methods learn a policy by iteratively performing multiple mini-batch optimization epochs of a surrogate objective with one…”
Get full text

In Defense of the Unitary Scalarization for Deep Multi-Task Learning by Kurin, Vitaly, De Palma, Alessandro, Kostrikov, Ilya, Whiteson, Shimon, Kumar, M. Pawan

“…Recent multi-task learning research argues against unitary scalarization, where training simply minimizes the sum of the task losses. Several ad-hoc multi-task…”
Get full text

Can $Q$-Learning with Graph Networks Learn a Generalizable Branching Heuristic for a SAT Solver? by Kurin, Vitaly, Godil, Saad, Whiteson, Shimon, Catanzaro, Bryan

“…We present Graph-$Q$-SAT, a branching heuristic for a Boolean SAT solver trained with value-based reinforcement learning (RL) using Graph Neural Networks for…”
Get full text

A Generalist Neural Algorithmic Learner by Ibarz, Borja, Kurin, Vitaly, Papamakarios, George, Nikiforou, Kyriacos, Bennani, Mehdi, Csordás, Róbert, Dudzik, Andrew, Bošnjak, Matko, Vitvitskyi, Alex, Rubanova, Yulia, Deac, Andreea, Bevilacqua, Beatrice, Ganin, Yaroslav, Blundell, Charles, Veličković, Petar

“…The cornerstone of neural algorithmic reasoning is the ability to solve algorithmic tasks, especially in a way that generalises out of distribution. While…”
Get full text

MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research by Samvelyan, Mikayel, Kirk, Robert, Kurin, Vitaly, Parker-Holder, Jack, Jiang, Minqi, Hambro, Eric, Petroni, Fabio, Küttler, Heinrich, Grefenstette, Edward, Rocktäschel, Tim

“…Progress in deep reinforcement learning (RL) is heavily driven by the availability of challenging benchmarks used for training agents. However, benchmarks that…”
Get full text

The Atari Grand Challenge Dataset by Kurin, Vitaly, Nowozin, Sebastian, Hofmann, Katja, Beyer, Lucas, Leibe, Bastian

“…Recent progress in Reinforcement Learning (RL), fueled by its combination, with Deep Learning has enabled impressive results in learning to interact with…”
Get full text

Towards a Principled Integration of Multi-Camera Re-Identification and Tracking through Optimal Bayes Filters by Beyer, Lucas, Breuers, Stefan, Kurin, Vitaly, Leibe, Bastian

“…With the rise of end-to-end learning through deep learning, person detectors and re-identification (ReID) models have recently become very strong. Multi-camera…”
Get full text

Fast Context Adaptation via Meta-Learning by Zintgraf, Luisa M, Shiarlis, Kyriacos, Kurin, Vitaly, Hofmann, Katja, Whiteson, Shimon

“…We propose CAVIA for meta-learning, a simple extension to MAML that is less prone to meta-overfitting, easier to parallelise, and more interpretable. CAVIA…”
Get full text

Insights From the NeurIPS 2021 NetHack Challenge by Hambro, Eric, Mohanty, Sharada, Babaev, Dmitrii, Byeon, Minwoo, Chakraborty, Dipam, Grefenstette, Edward, Jiang, Minqi, Jo, Daejin, Kanervisto, Anssi, Kim, Jongmin, Kim, Sungwoong, Kirk, Robert, Kurin, Vitaly, Küttler, Heinrich, Kwon, Taehwon, Lee, Donghoon, Mella, Vegard, Nardelli, Nantas, Nazarov, Ivan, Ovsov, Nikita, Parker-Holder, Jack, Raileanu, Roberta, Ramanauskas, Karolis, Rocktäschel, Tim, Rothermel, Danielle, Samvelyan, Mikayel, Sorokin, Dmitry, Sypetkowski, Maciej, Sypetkowski, Michał

“…In this report, we summarize the takeaways from the first NeurIPS 2021 NetHack Challenge. Participants were tasked with developing a program or agent that can…”
Get full text

Learning from Demonstration in the Wild by Behbahani, Feryal, Shiarlis, Kyriacos, Chen, Xi, Kurin, Vitaly, Kasewa, Sudhanshu, Stirbu, Ciprian, Gomes, João, Paul, Supratik, Oliehoek, Frans A, Messias, João, Whiteson, Shimon

“…Learning from demonstration (LfD) is useful in settings where hand-coding behaviour or a reward function is impractical. It has succeeded in a wide range of…”
Get full text