Search Results - "Castellini, Jacopo"

Analysing factorizations of action-value networks for cooperative multi-agent reinforcement learning by Castellini, Jacopo, Oliehoek, Frans A., Savani, Rahul, Whiteson, Shimon

“…Recent years have seen the application of deep reinforcement learning techniques to cooperative multi-agent systems, with great empirical success. However,…”
Get full text

Krylov iterative methods for the geometric mean of two matrices times a vector by Castellini, Jacopo

“…In this work, we are presenting an efficient way to compute the geometric mean of two positive definite matrices times a vector. For this purpose, we are…”
Get full text

Difference rewards policy gradients by Castellini, Jacopo, Devlin, Sam, Oliehoek, Frans A., Savani, Rahul

“…Abstract Policy gradient methods have become one of the most popular classes of algorithms for multi-agent reinforcement learning. A key challenge, however,…”
Get full text

Improved Representations for Cooperative Multi-Agent Reinforcement Learning by Castellini, Jacopo

“…Multi-agent systems [33, 136] are an ubiquitous presence in our everyday life: our entire society could be seen as a huge multi-agent system in which each…”
Get full text

Learning Numeracy: Binary Arithmetic with Neural Turing Machines by Castellini, Jacopo

“…One of the main problems encountered so far with recurrent neural networks is that they struggle to retain long-time information dependencies in their…”
Get full text

Krylov Iterative Methods for the Geometric Mean of Two Matrices Times a Vector by Castellini, Jacopo

“…Numerical Algorithms 74(2), 561-571, Springer, 2017 In this work, we are presenting an efficient way to compute the geometric mean of two positive definite…”
Get full text

On Convex Optimal Value Functions For POSGs by Cunha, Rafael F, Castellini, Jacopo, Peralez, Johan, Dibangoye, Jilles S

“…Multi-agent planning and reinforcement learning can be challenging when agents cannot see the state of the world or communicate with each other due to…”
Get full text

Analysing Factorizations of Action-Value Networks for Cooperative Multi-Agent Reinforcement Learning by Castellini, Jacopo, Oliehoek, Frans A, Savani, Rahul, Whiteson, Shimon

“…Auton Agent Multi-Agent Syst 35, 25 (2021) Recent years have seen the application of deep reinforcement learning techniques to cooperative multi-agent systems,…”
Get full text

Difference Rewards Policy Gradients by Castellini, Jacopo, Devlin, Sam, Oliehoek, Frans A, Savani, Rahul

“…Neural Comput & Applic (2022) Policy gradient methods have become one of the most popular classes of algorithms for multi-agent reinforcement learning. A key…”
Get full text

Optimally Solving Simultaneous-Move Dec-POMDPs: The Sequential Central Planning Approach by Peralez, Johan, Delage, Aurélien, Castellini, Jacopo, Cunha, Rafael F, Dibangoye, Jilles S

“…Centralized training for decentralized execution paradigm emerged as the state-of-the-art approach to epsilon-optimally solving decentralized partially…”
Get full text