PKU-MARL/Multi-Agent-Transformer

Issues

• How to get the replay file(StarCraft2)

  #37 opened 4 months ago by HaHaRen6
  0

• Question about the monotonic improvement guarantee of MAT.

  #36 opened 5 months ago by CrazySssst
  0

• details about the decoder architecture

  #35 opened 6 months ago by geruome
  0

• Centralized Execution VS Single Agent Reinforcement Learning

  #34 opened 7 months ago by brithbutter
  0

• Python Version

  #22 opened a year ago by saptab
  5

• The algorithm crashes when run multiple times at the same time

  #33 opened 7 months ago by be-well
  0

• Question about MAT's result on SMAC corridor

  #32 opened 7 months ago by amorphophallus
  0

• Question about causal attention in decoder

  #31 opened 7 months ago by Porthoos
  0

• State (cent obs) not used in evaluate actions

  #30 opened 8 months ago by brithbutter
  0

• A simple question about MAT

  #29 opened 9 months ago by KID0031
  0

• Config Setting on Bi-DexHands domain

  #28 opened 9 months ago by JensenLZX
  2

• Add for randomizing agent order in RandomStarCraft2Env Multi map env

  #26 opened 10 months ago by Yuxin916
  1

• Using MAT for a partially observable cooperative multi agent setting with macro actions

  #18 opened 9 months ago by mylad13
  2

• Transformer memory

  #17 opened 9 months ago by rsanchezmo
  4

• Whether the code realizes the shuffling of the agent order？

  #24 opened 9 months ago by zhx0506
  4

• linux version

  #25 opened 10 months ago by jeffreyyyyyyyyy
  1

• 您好MAR是否有迁移学习的效果？

  #27 opened 9 months ago by hj5717
  0

• Questions about MAMujoco

  #23 opened 10 months ago by kaiyama12345679
  4

• Question on excellent few-short learner on tasks regardless of changes in the number of agents

  #20 opened 10 months ago by Yuxin916
  2

• The dependence installation file should be "requirement.txt", not "requirment.txt" without "e".

  #21 opened 10 months ago by orange1111111
  1

• Other Implementations

  #5 opened 2 years ago by aidanmclaughlin
  6

• SMAC pre-trained models

  #19 opened a year ago by ubinjin
  0

• Problem about results in SMAC

  #15 opened a year ago by mrqy0610
  3

• Inquiry about MAT Generalization Experiment Scripts

  #10 opened 2 years ago by fyqqyf
  5

• Some questions about MAT-dec

  #16 opened a year ago by lingxiao-guo
  3

• Unable to reproduce the experimental results.

  #14 opened 2 years ago by LiuChXX
  2

• Problem about result in Bi-dexHands environment

  #12 opened 2 years ago by mrqy0610
  2

• Why the dimension of discrete action should be action_dim + 1

  #11 opened 2 years ago by Metro1998
  2

• Questions about the training and execution paradigm?

  #13 opened 2 years ago by BigBearBlacken
  2

• What does "mat_gru","mat_decoder" and "mat_encoder" mean in the code

  #9 opened 2 years ago by fyqqyf
  2

• State Dim for MultiAgentTransformer Class

  #8 opened 2 years ago by tsung-jui-wu
  1

• What's the "faulty node" mean?

  #7 opened 2 years ago by JunjunjunHJ
  0

• Question about MAT-Dec

  #6 opened 2 years ago by DongChen06
  2

• Difference Between Parallel Act and Autoregressive Act

  #3 opened 2 years ago by tsung-jui-wu
  2

• test for notification

  #4 opened 2 years ago by morning9393
  0

• The reason for superior performance on heterogeneous-agent tasks

  #2 opened 2 years ago by zerlinwang
  2

• Arbitrary Sequences

  #1 opened 2 years ago by tsung-jui-wu
  1