CoSER adaptively samples joint actions in CTDE MARL to reduce sampling error relative to the joint on-policy distribution, empirically improving reliability of independent policy gradient convergence.
Episodic multi-agent reinforcement learning with curiosity- driven exploration
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2025 2verdicts
UNVERDICTED 2representative citing papers
The Focusing Influence Mechanism (FIM) uses an entropy-based criterion and eligibility traces to help multiple agents in reinforcement learning focus and maintain their influence on under-explored parts of the state space, improving coordinated exploration and performance under sparse rewards.
citing papers explorer
-
Centralized Adaptive Sampling for Reliable Co-Training of Independent Multi-Agent Policies
CoSER adaptively samples joint actions in CTDE MARL to reduce sampling error relative to the joint on-policy distribution, empirically improving reliability of independent policy gradient convergence.
-
Focusing Influence Mechanism for Multi-Agent Reinforcement Learning
The Focusing Influence Mechanism (FIM) uses an entropy-based criterion and eligibility traces to help multiple agents in reinforcement learning focus and maintain their influence on under-explored parts of the state space, improving coordinated exploration and performance under sparse rewards.