177 citations · 317 across the 13 of their papers we have counts for
14 papers
A Generalist Neural Algorithmic Learner
Borja Ibarz, Vitaly Kurin, George Papamakarios +12
The cornerstone of neural algorithmic reasoning is the ability to solve algorithmic tasks, especially in a way that generalises out of distribution. While recent years have seen a…
Insights From the NeurIPS 2021 NetHack Challenge
Eric Hambro, Sharada Mohanty, Dmitrii Babaev +26
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 win (i.e., 'ascend' i…
You May Not Need Ratio Clipping in PPO
Mingfei Sun, Vitaly Kurin, Guoqing Liu +4
Proximal Policy Optimization (PPO) methods learn a policy by iteratively performing multiple mini-batch optimization epochs of a surrogate objective with one set of sampled data. R…
In Defense of the Unitary Scalarization for Deep Multi-Task Learning
Vitaly Kurin, Alessandro De Palma, Ilya Kostrikov +2
Recent multi-task learning research argues against unitary scalarization, where training simply minimizes the sum of the task losses. Several ad-hoc multi-task optimization algorit…
MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research
Mikayel Samvelyan, Robert Kirk, Vitaly Kurin +7
Progress in deep reinforcement learning (RL) is heavily driven by the availability of challenging benchmarks used for training agents. However, benchmarks that are widely adopted b…
Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezing
Charlie Blake, Vitaly Kurin, Maximilian Igl +1
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 (MLP), with superior…
My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control
Vitaly Kurin, Maximilian Igl, Tim Rocktäschel +2
Multitask Reinforcement Learning is a promising way to obtain models with better performance, generalisation, data efficiency, and robustness. Most existing work is limited to comp…
Deep Coordination Graphs
Wendelin Böhmer, Vitaly Kurin, Shimon Whiteson
This paper introduces the deep coordination graph (DCG) for collaborative multi-agent reinforcement learning. DCG strikes a flexible trade-off between representational capacity and…
Can -Learning with Graph Networks Learn a Generalizable Branching Heuristic for a SAT Solver?
Vitaly Kurin, Saad Godil, Shimon Whiteson +1
We present Graph--SAT, a branching heuristic for a Boolean SAT solver trained with value-based reinforcement learning (RL) using Graph Neural Networks for function approximation…
Fast Efficient Hyperparameter Tuning for Policy Gradients
Supratik Paul, Vitaly Kurin, Shimon Whiteson
The performance of policy gradient methods is sensitive to hyperparameter settings that must be tuned for any new application. Widely used grid search methods for tuning hyperparam…
Learning from Demonstration in the Wild
Feryal Behbahani, Kyriacos Shiarlis, Xi Chen +8
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 problems but typically…
Fast Context Adaptation via Meta-Learning
Luisa M Zintgraf, Kyriacos Shiarlis, Vitaly Kurin +2
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 partitions the model par…
The Atari Grand Challenge Dataset
Vitaly Kurin, Sebastian Nowozin, Katja Hofmann +2
Recent progress in Reinforcement Learning (RL), fueled by its combination, with Deep Learning has enabled impressive results in learning to interact with complex virtual environmen…
Towards a Principled Integration of Multi-Camera Re-Identification and Tracking through Optimal Bayes Filters
Lucas Beyer, Stefan Breuers, Vitaly Kurin +1
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 multi-target (MCMT)…