G
Gregory Farquhar
Researcher at University of Oxford
Publications - 36
Citations - 4330
Gregory Farquhar is an academic researcher from University of Oxford. The author has contributed to research in topics: Reinforcement learning & Estimator. The author has an hindex of 19, co-authored 35 publications receiving 2743 citations. Previous affiliations of Gregory Farquhar include Facebook.
Papers
More filters
Proceedings Article
Counterfactual Multi−Agent Policy Gradients
TL;DR: In this paper, a multi-agent actor-critic method called counterfactual multiagent (COMA) policy gradients is proposed, which uses a centralised critic to estimate the Q-function and decentralised actors to optimise the agents' policies.
Posted Content
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
Tabish Rashid,Mikayel Samvelyan,Christian Schroeder de Witt,Gregory Farquhar,Jakob Foerster,Shimon Whiteson +5 more
TL;DR: In this article, the authors propose a value-based method that can train decentralised policies in a centralised end-to-end fashion in simulated or laboratory settings, where global state information is available and communication constraints are lifted.
Proceedings Article
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
Tabish Rashid,Mikayel Samvelyan,Christian Schroeder,Gregory Farquhar,Jakob Foerster,Shimon Whiteson +5 more
TL;DR: QMIX employs a network that estimates joint action-values as a complex non-linear combination of per-agent values that condition only on local observations, and structurally enforce that the joint-action value is monotonic in the per- agent values, which allows tractable maximisation of the jointaction-value in off-policy learning.
Posted Content
Counterfactual Multi-Agent Policy Gradients
TL;DR: A new multi-agent actor-critic method called counterfactual multi- agent (COMA) policy gradients, which uses a centralised critic to estimate the Q-function and decentralised actors to optimise the agents' policies.
Proceedings Article
The StarCraft Multi-Agent Challenge
Mikayel Samvelyan,Tabish Rashid,Christian Schroeder de Witt,Gregory Farquhar,Nantas Nardelli,Tim G. J. Rudner,Chia-Man Hung,Philip H. S. Torr,Jakob Foerster,Shimon Whiteson +9 more
TL;DR: The StarCraft Multi-Agent Challenge (SMAC), based on the popular real-time strategy game StarCraft II, is proposed as a benchmark problem and an open-source deep multi-agent RL learning framework including state-of-the-art algorithms is opened.