Observation and action delays are formally equivalent in cooperative Dec-POMDPs, yielding identical optimal solutions and enabling zero-shot transfer, though learning dynamics differ due to credit assignment and operational constraints.
Delay-aware multi- agent reinforcement learning for cooperative and competitive environments
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
Prudent-Banker achieves pseudo-regret Õ(√T + √D) and Õ(1) regret vs. safe comparator in adversarial bandits both with and without delays, matching new lower bounds up to logs.
Institutional delays trigger instability in multi-agent systems through delayed repression, with simulations identifying reactivity to lagged signals as the destabilizing factor rather than learning.
Energy-aware MARL with individual rewards for drone networks shows better robustness to larger environments and more agents than shared-reward baselines in simulations, reaching at least 80% success rate.
citing papers explorer
-
Structural Equivalence and Learning Dynamics in Delayed MARL
Observation and action delays are formally equivalent in cooperative Dec-POMDPs, yielding identical optimal solutions and enabling zero-shot transfer, though learning dynamics differ due to credit assignment and operational constraints.
-
Prudent-Banker: No Extra Fees for Baseline Safety in Adversarial Bandits With and Without Delays
Prudent-Banker achieves pseudo-regret Õ(√T + √D) and Õ(1) regret vs. safe comparator in adversarial bandits both with and without delays, matching new lower bounds up to logs.
-
Delayed Repression and Emergent Instability in Adaptive Multi-Agent Systems
Institutional delays trigger instability in multi-agent systems through delayed repression, with simulations identifying reactivity to lagged signals as the destabilizing factor rather than learning.
-
Scaling up Energy-Aware Multi-Agent Reinforcement Learning for Mission-Oriented Drone Networks with Individual Reward
Energy-aware MARL with individual rewards for drone networks shows better robustness to larger environments and more agents than shared-reward baselines in simulations, reaching at least 80% success rate.