C
Christian Schroeder
Researcher at University of Oxford
Publications - 2
Citations - 507
Christian Schroeder is an academic researcher from University of Oxford. The author has contributed to research in topics: Reinforcement learning & Domain knowledge. The author has an hindex of 2, co-authored 2 publications receiving 506 citations.
Papers
More filters
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.
Proceedings Article
Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning
TL;DR: The authorsIL The authors proposes to utilize value function factoring with random subsets of entities in each factor as an auxiliary objective in order to disentangle value predictions from irrelevant entities.