Darl1n: Distributed multi-agent reinforcement learning with one-hop neighbors

B Wang, J Xie, N Atanasov - 2022 IEEE/RSJ International …, 2022 - ieeexplore.ieee.org
Multi-agent reinforcement learning (MARL) meth-ods face a curse of dimensionality in the
policy and value function representations as the number of agents increases. The …
被引用次数：12 相关文章
[PDF] existentialrobotics.org

[PDF][PDF] DARL1N: Distributed multi-Agent Reinforcement Learning with One-hop Neighbors

B Wang, J Xie, N Atanasov - existentialrobotics.org
Multi-agent reinforcement learning (MARL) methods face a curse of dimensionality in the
policy and value function representations as the number of agents increases. The …

DARL1N: Distributed multi-Agent Reinforcement Learning with One-hop Neighbors

B Wang, J Xie, N Atanasov - arXiv preprint arXiv:2202.09019, 2022 - arxiv.org
Most existing multi-agent reinforcement learning (MARL) methods are limited in the scale of
problems they can handle. Particularly, with the increase of the number of agents, their …
[PDF] github.io

[PDF][PDF] DARL1N: Distributed multi-Agent Reinforcement Learning with One-hop Neighbors

B Wang, J Xie, N Atanasov - natanaso.github.io
Multi-agent reinforcement learning (MARL) methods face a curse of dimensionality in the
policy and value function representations as the number of agents increases. The …

DARL1N: Distributed multi-Agent Reinforcement Learning with One-hop Neighbors

B Wang, J Xie, N Atanasov - arXiv e-prints, 2022 - ui.adsabs.harvard.edu
Most existing multi-agent reinforcement learning (MARL) methods are limited in the scale of
problems they can handle. Particularly, with the increase of the number of agents, their …
[PDF] nsf.gov

[PDF][PDF] DARL1N: Distributed multi-Agent Reinforcement Learning with One-hop Neighbors

B Wang, J Xie, N Atanasov - 2022 IEEE/RSJ International Conference on …, 2022 - par.nsf.gov
Multi-agent reinforcement learning (MARL) methods face a curse of dimensionality in the
policy and value function representations as the number of agents increases. The …
[PDF] ucsd.edu

[PDF][PDF] DARL1N: Distributed multi-Agent Reinforcement Learning with One-hop Neighbors

B Wang, J Xie, N Atanasov - erl.ucsd.edu
Multi-agent reinforcement learning (MARL) methods face a curse of dimensionality in the
policy and value function representations as the number of agents increases. The …