Alert button
Picture for Mikayel Samvelyan

Mikayel Samvelyan

Alert button

Multi-Agent Diagnostics for Robustness via Illuminated Diversity

Jan 24, 2024
Mikayel Samvelyan, Davide Paglieri, Minqi Jiang, Jack Parker-Holder, Tim Rocktäschel

Viaarxiv icon

JaxMARL: Multi-Agent RL Environments in JAX

Nov 20, 2023
Alexander Rutherford, Benjamin Ellis, Matteo Gallici, Jonathan Cook, Andrei Lupu, Gardar Ingvarsson, Timon Willi, Akbir Khan, Christian Schroeder de Witt, Alexandra Souly, Saptarashmi Bandyopadhyay, Mikayel Samvelyan, Minqi Jiang, Robert Tjarko Lange, Shimon Whiteson, Bruno Lacerda, Nick Hawes, Tim Rocktaschel, Chris Lu, Jakob Nicolaus Foerster

Viaarxiv icon

Mix-ME: Quality-Diversity for Multi-Agent Learning

Nov 03, 2023
Garðar Ingvarsson, Mikayel Samvelyan, Bryan Lim, Manon Flageat, Antoine Cully, Tim Rocktäschel

Viaarxiv icon

MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning

Mar 06, 2023
Mikayel Samvelyan, Akbir Khan, Michael Dennis, Minqi Jiang, Jack Parker-Holder, Jakob Foerster, Roberta Raileanu, Tim Rocktäschel

Figure 1 for MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning
Figure 2 for MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning
Figure 3 for MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning
Figure 4 for MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning
Viaarxiv icon

SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning

Dec 14, 2022
Benjamin Ellis, Skander Moalla, Mikayel Samvelyan, Mingfei Sun, Anuj Mahajan, Jakob N. Foerster, Shimon Whiteson

Figure 1 for SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning
Figure 2 for SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning
Figure 3 for SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning
Figure 4 for SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning
Viaarxiv icon

Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning

Jul 23, 2022
Michael Matthews, Mikayel Samvelyan, Jack Parker-Holder, Edward Grefenstette, Tim Rocktäschel

Figure 1 for Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning
Figure 2 for Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning
Figure 3 for Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning
Figure 4 for Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning
Viaarxiv icon

GriddlyJS: A Web IDE for Reinforcement Learning

Jul 13, 2022
Christopher Bamford, Minqi Jiang, Mikayel Samvelyan, Tim Rocktäschel

Figure 1 for GriddlyJS: A Web IDE for Reinforcement Learning
Figure 2 for GriddlyJS: A Web IDE for Reinforcement Learning
Figure 3 for GriddlyJS: A Web IDE for Reinforcement Learning
Figure 4 for GriddlyJS: A Web IDE for Reinforcement Learning
Viaarxiv icon

Insights From the NeurIPS 2021 NetHack Challenge

Mar 22, 2022
Eric Hambro, Sharada Mohanty, Dmitrii Babaev, Minwoo Byeon, Dipam Chakraborty, Edward Grefenstette, Minqi Jiang, Daejin Jo, Anssi Kanervisto, Jongmin Kim, Sungwoong Kim, Robert Kirk, Vitaly Kurin, Heinrich Küttler, Taehwon Kwon, Donghoon Lee, Vegard Mella, Nantas Nardelli, Ivan Nazarov, Nikita Ovsov, Jack Parker-Holder, Roberta Raileanu, Karolis Ramanauskas, Tim Rocktäschel, Danielle Rothermel, Mikayel Samvelyan, Dmitry Sorokin, Maciej Sypetkowski, Michał Sypetkowski

Figure 1 for Insights From the NeurIPS 2021 NetHack Challenge
Figure 2 for Insights From the NeurIPS 2021 NetHack Challenge
Figure 3 for Insights From the NeurIPS 2021 NetHack Challenge
Figure 4 for Insights From the NeurIPS 2021 NetHack Challenge
Viaarxiv icon

Evolving Curricula with Regret-Based Environment Design

Mar 08, 2022
Jack Parker-Holder, Minqi Jiang, Michael Dennis, Mikayel Samvelyan, Jakob Foerster, Edward Grefenstette, Tim Rocktäschel

Figure 1 for Evolving Curricula with Regret-Based Environment Design
Figure 2 for Evolving Curricula with Regret-Based Environment Design
Figure 3 for Evolving Curricula with Regret-Based Environment Design
Figure 4 for Evolving Curricula with Regret-Based Environment Design
Viaarxiv icon

Generalization in Cooperative Multi-Agent Systems

Jan 31, 2022
Anuj Mahajan, Mikayel Samvelyan, Tarun Gupta, Benjamin Ellis, Mingfei Sun, Tim Rocktäschel, Shimon Whiteson

Figure 1 for Generalization in Cooperative Multi-Agent Systems
Figure 2 for Generalization in Cooperative Multi-Agent Systems
Figure 3 for Generalization in Cooperative Multi-Agent Systems
Figure 4 for Generalization in Cooperative Multi-Agent Systems
Viaarxiv icon