Folgen
Mikayel Samvelyan
Mikayel Samvelyan
UCL & Meta AI
Bestätigte E-Mail-Adresse bei meta.com - Startseite
Titel
Zitiert von
Zitiert von
Jahr
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
T Rashid, M Samvelyan, CS De Witt, G Farquhar, J Foerster, S Whiteson
ICML 2018, 2018
11972018
The StarCraft Multi-Agent Challenge
M Samvelyan, T Rashid, CS de Witt, G Farquhar, N Nardelli, TGJ Rudner, ...
AAMAS 2019, 2019
4762019
MAVEN: Multi-Agent Variational Exploration
A Mahajan, T Rashid, M Samvelyan, S Whiteson
NeurIPS 2019, 2019
2192019
MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research
M Samvelyan, R Kirk, V Kurin, J Parker-Holder, M Jiang, E Hambro, ...
NeurIPS 2021, 2021
362021
Evolving Curricula with Regret-Based Environment Design
J Parker-Holder, M Jiang, M Dennis, M Samvelyan, J Foerster, ...
ICML 2022, 2022
262022
Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning
A Mahajan, M Samvelyan, L Mao, V Makoviychuk, A Garg, J Kossaifi, ...
ICML 2021, 2021
192021
Generalization in cooperative multi-agent systems
A Mahajan, M Samvelyan, T Gupta, B Ellis, M Sun, T Rocktäschel, ...
arXiv preprint arXiv:2202.00104, 2022
62022
Insights From the NeurIPS 2021 NetHack Challenge
E Hambro, S Mohanty, D Babaev, M Byeon, D Chakraborty, ...
NeurIPS 2021 Competitions and Demonstrations Track, 2022
32022
SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning
B Ellis, S Moalla, M Samvelyan, M Sun, A Mahajan, JN Foerster, ...
arXiv preprint arXiv:2212.07489, 2022
22022
Random Irregular Block-Hierarchical Networks: Algorithms for Computation of Main Properties
S Avetisyan, M Samvelyan, M Karapetyan
IX Annual Scientific Conference at Russian-Armenian University, 2015
22015
Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning
M Matthews, M Samvelyan, J Parker-Holder, E Grefenstette, ...
CoLLAs 2022, 2022
12022
SkillHack: A Benchmark for Skill Transfer in Open-Ended Reinforcement Learning
M Matthews, M Samvelyan, J Parker-Holder, E Grefenstette, ...
Workshop on Agent Learning in Open-Endedness @ ICLR 2022, 2022
12022
MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning
M Samvelyan, A Khan, MD Dennis, M Jiang, J Parker-Holder, JN Foerster, ...
Deep Reinforcement Learning Workshop @ NeurIPS 2022, 2022
12022
GriddlyJS: A Web IDE for Reinforcement Learning
C Bamford, M Jiang, M Samvelyan, T Rocktäschel
NeurIPS 2022, 2022
2022
Reinforcement Learning in Factored Action Spaces using Tensor Decompositions
A Mahajan, M Samvelyan, L Mao, V Makoviychuk, A Garg, J Kossaifi, ...
arXiv preprint arXiv:2110.14538, 2021
2021
That Escalated Quickly: Compounding Complexity by Editing Levels at the Frontier of Agent Capabilities
J Parker-Holder, M Jiang, MD Dennis, M Samvelyan, JN Foerster, ...
Deep Reinforcement Learning Workshop @ NeurIPS 2021, 2021
2021
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–16