6 citations · 18 across the 10 of their papers we have counts for
8 papers · 1 filter
Reinforcement Learning with Fast and Forgetful Memory
Steven Morad, Ryan Kortvelesy, Stephan Liwicki +1
Nearly all real world tasks are inherently partially observable, necessitating the use of memory in Reinforcement Learning (RL). Most model-free approaches summarize the trajectory…
Fixed Integral Neural Networks
Ryan Kortvelesy
It is often useful to perform integration over learned functions represented by neural networks. However, this integration is usually performed numerically, as analytical integrati…
Generalised f-Mean Aggregation for Graph Neural Networks
Ryan Kortvelesy, Steven Morad, Amanda Prorok
Graph Neural Network (GNN) architectures are defined by their implementations of update and aggregation modules. While many works focus on new ways to parametrise the update module…
POPGym: Benchmarking Partially Observable Reinforcement Learning
Steven Morad, Ryan Kortvelesy, Matteo Bettini +2
Real world applications of Reinforcement Learning (RL) are often partially observable, thus requiring memory. Despite this, partial observability is still largely ignored by contem…
Permutation-Invariant Set Autoencoders with Fixed-Size Embeddings for Multi-Agent Learning
Ryan Kortvelesy, Steven Morad, Amanda Prorok
The problem of permutation-invariant learning over set representations is particularly relevant in the field of multi-agent systems -- a few potential applications include unsuperv…
QGNN: Value Function Factorisation with Graph Neural Networks
Ryan Kortvelesy, Amanda Prorok
In multi-agent reinforcement learning, the use of a global objective is a powerful tool for incentivising cooperation. Unfortunately, it is not sample-efficient to train individual…
Graph Convolutional Memory using Topological Priors
Steven D. Morad, Stephan Liwicki, Ryan Kortvelesy +2
Solving partially-observable Markov decision processes (POMDPs) is critical when applying reinforcement learning to real-world problems, where agents have an incomplete view of the…
ModGNN: Expert Policy Approximation in Multi-Agent Systems with a Modular Graph Neural Network Architecture
Ryan Kortvelesy, Amanda Prorok
Recent work in the multi-agent domain has shown the promise of Graph Neural Networks (GNNs) to learn complex coordination strategies. However, most current approaches use minor var…