0

Local Advantage Networks for Multi-Agent Reinforcement Learning in Dec-POMDPs
Many recent successful off-policy multi-agent reinforcement learning (MARL) algorithms for cooperative partially observable …
Raphael Avalos, Mathieu Reymond, Ann Nowe, Diederik M. Roijers
PDF Cite
Autocurricula and Emergent Sociality from a Gene Perspective
The competitive and cooperative forces of natural selection have driven the evolution of intelligence for many millions of years, …
Andries Rosseau, Raphael Avalos, Ann Nowe
PDF Cite Video
Multi-agent RMax for Multi-Agent Multi-Armed Bandits
In this paper, we provide PAC bounds for best-arm identification in multi-agent multi-armed bandits (MAMABs), via an algorithm we call …
Eugenio Bargiacchi, Raphael Avalos, Timothy Verstraeten, Pieter Libin, Ann Nowe, Diederik M. Roijers
PDF Cite Video
The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Models
Partially Observable Markov Decision Processes (POMDPs) are useful tools to model environments where the full state cannot be perceived …
Raphael Avalos, Florent Delgrange, Ann Nowe, Guillermo Perez, Diederik M. Roijers
PDF Cite