Corpus ID: 214623190

Multi-Agent Reinforcement Learning for Problems with Combined Individual and Team Reward

@article{Sheikh2020MultiAgentRL,
  title={Multi-Agent Reinforcement Learning for Problems with Combined Individual and Team Reward},
  author={Hassam Ullah Sheikh and Ladislau B{\"o}l{\"o}ni},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.10598}
}
  • Hassam Ullah Sheikh, Ladislau Bölöni
  • Published 2020
  • Computer Science
  • ArXiv
  • Many cooperative multi-agent problems require agents to learn individual tasks while contributing to the collective success of the group. This is a challenging task for current state-of-the-art multi-agent reinforcement algorithms that are designed to either maximize the global reward of the team or the individual local rewards. The problem is exacerbated when either of the rewards is sparse leading to unstable learning. To address this problem, we present Decomposed Multi-Agent Deep… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 32 REFERENCES

    Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Cooperative Multi-Agent Learning: The State of the Art