Shunyu 的博客 | Shunyu's Blog

强化学习论文（12）SchedNet

Learning to Schedule Communication in Multi-agent Reinforcement Learning

标签： SchedNet; actor-critic; off-policy; model-free; communication; continuous communication channel; discrete action space; continuous state space; cooperative task; centralized training with dece...

Posted by Shunyu on June 28, 2020

强化学习论文（11）ATOC

Learning Attentional Communication for Multi-Agent Cooperation

标签： ATOC; actor-critic; off-policy; model-free; communication; continuous communication channel; continuous action space; continuous state space; cooperative task; centralized training with decent...

Posted by Shunyu on June 23, 2020

强化学习论文（10）QTRAN

QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement learning

标签： QTRAN; value-based; off-policy; model-free; discrete action space; continuous state space; cooperative task; credit assignment; centralized training with decentralized execution; value functio...

Posted by Shunyu on June 19, 2020

强化学习论文（9）QMIX

QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

标签： QMIX; value-based; off-policy; model-free; discrete action space; continuous state space; cooperative task; credit assignment; centralized training with decentralized execution; value function...

Posted by Shunyu on June 18, 2020

强化学习论文（8）VDN

Value-Decomposition Networks For Cooperative Multi-Agent Learning

标签： VDN; value-based; off-policy; model-free; communication; continuous communication channel; discrete action space; continuous state space; cooperative task; credit assignment; centralized train...

Posted by Shunyu on June 17, 2020

强化学习论文（7）COMA

Counterfactual Multi-Agent Policy Gradients

标签： COMA; actor-critic; on-policy; model-free; communication; continuous communication channel; discrete action space; continuous state space; cooperative task; credit assignment; centralized trai...

Posted by Shunyu on June 16, 2020

强化学习论文（6）DCC-MD&MADDPG-MD

Message-Dropout: An Efficient Training Method for Multi-Agent Deep Reinforcement Learning

标签： DCC-MD; value-based; discrete action space; decentralized approach; MADDPG-MD; actor-critic; continuous action space; centralized training with decentralized execution; off-policy; model-fre...

Posted by Shunyu on June 10, 2020

强化学习论文（5）MD-MADDPG

Improving coordination in small-scale multi-agent deep reinforcement learning through memory-driven communication

标签： MD-MADDPG; actor-critic; off-policy; model-free; communication; continuous communication channel; continuous action space; continuous state space; cooperative task; centralized training with d...

Posted by Shunyu on June 10, 2020

强化学习论文（4）BiCNet

Multiagent Bidirectionally-Coordinated Nets Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games

标签： BiCNet; actor-critic; off-policy; model-free; communication; continuous communication channel; continuous action space; continuous state space; cooperative task; centralized approach; multi-ag...

Posted by Shunyu on June 6, 2020

强化学习论文（3）CommNet

Learning Multiagent Communication with Backpropagation

标签： CommNet; policy-based; on-policy; model-free; communication; continuous communication channel; discrete action space; continuous state space; cooperative task; centralized approach; multi-agen...

Posted by Shunyu on June 5, 2020

Shunyu's Blog