method · first seen 13 Oct 2026
dueling double DQN
Also: dueling double deep Q-network
A deep Q-learning variant separating value and advantage streams and reducing overestimation via double estimation.
Mentions per week
PapersCodeDiscussion
Earliest sources
- When Does Opponent Modeling Pay Off? Spatial Inference Stabilises Reinforcement Learning under Partial ObservabilityPapers · 13 Oct 2026 · Marcel Petran, Stefan Edelkamp
Latest sources
- When Does Opponent Modeling Pay Off? Spatial Inference Stabilises Reinforcement Learning under Partial ObservabilityPapers · 13 Oct 2026 · Marcel Petran, Stefan Edelkamp