Pith. sign in

Leibo, Karl Tuyls, and Thore Grae- pel

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.MA 1

years

2025 1

verdicts

REJECT 1

representative citing papers

Double Distillation Network for Multi-Agent Reinforcement Learning

cs.MA · 2025-02-05 · reject · novelty 5.0

DDN, a double distillation network for cooperative MARL, claims to eliminate CTDE inherent error via global-to-local knowledge distillation and an RND-style intrinsic reward, with better SMAC and Predator-Prey win rates.

citing papers explorer

Showing 1 of 1 citing paper.

  • Double Distillation Network for Multi-Agent Reinforcement Learning cs.MA · 2025-02-05 · reject · none · ref 14

    DDN, a double distillation network for cooperative MARL, claims to eliminate CTDE inherent error via global-to-local knowledge distillation and an RND-style intrinsic reward, with better SMAC and Predator-Prey win rates.