openai/maddpg

Issues

• Loading previous state...

  #70 opened 2 years ago by yanwaiwai
  1

• python3.5.4已经进行维护。

  #80 opened 3 months ago by vducd
  0

• How to save the videos of each 1000th episode ?

  #79 opened 5 months ago by longxilong
  0

• ModuleNotFoundError: No module named 'maddpg.common'

  #76 opened 9 months ago by yanmmmm
  0

• TypeError: set_color() got multiple values for argument 'alpha' in Simple-Crypto

  #30 opened 5 years ago by marwanihab
  6

• what's benchmark used for?

  #35 opened 5 years ago by AI-Science-Tech
  1

• DDPG action space vs multi-agent particle environment action space

  #71 opened 2 years ago by medhijk
  0

• Why ‘u_action_space = spaces.Discrete(world.dim_p * 2 + 1)’？

  #66 opened 3 years ago by ScorpioPeng
  2

• Trying to set the random seeds, any idea how?

  #45 opened 4 years ago by hossein-haeri
  1

• Two problem about update function

  #32 opened 5 years ago by YuanyeMa
  5

• A issue about the saving the model in train.py

  #69 opened 2 years ago by chengdusunny
  0

• Question about the way how to update actor

  #65 opened 3 years ago by choasLC
  1

• A question about maddpg.py

  #68 opened 2 years ago by chengdusunny
  0

• There is no provision to run ddpg.

  #33 opened 5 years ago by frenzytejask98
  3

• Training EVERY step, not every 100

  #67 opened 3 years ago by eflopez1
  1

• SoftMultiCategoricalPd

  #40 opened 4 years ago by sandeepnRES
  1

• How to normalize the data in table of Appendix to obtain Figure 3 in paper?

  #55 opened 4 years ago by flammingRaven
  1

• how to evaluate maddpg?

  #57 opened 3 years ago by Xinlei-Ren
  0

• The code does not converged

  #34 opened 5 years ago by sjq19960802
  1

• How to run ddpg

  #64 opened 3 years ago by EvaluationResearch
  0

• All scenario will fail but except scenario simple

  #63 opened 3 years ago by EvaluationResearch
  1

• Is policy ensambles implemented in this repository?

  #60 opened 3 years ago by 2015211289
  0

• ../../..

  #59 opened 3 years ago by devarani10
  0

• Using any scenario rather than the "simple" one gives error during loading the model after training

  #58 opened 3 years ago by dr-smgad
  0

• I have train it success but how to run? How to see the visible answer?

  #49 opened 4 years ago by zhijiejia
  2

• Can this algorithm be generalised to work with multiple (60) agents competing against eachother?

  #27 opened 3 years ago by alexanderkell
  2

• how to evaluate maddpg?

  #56 opened 3 years ago by Xinlei-Ren
  0

• Nontype flaw in "train.py", line 182

  #28 opened 5 years ago by DailinH
  3

• How can I use DDPG to train it?

  #53 opened 4 years ago by CHH3213
  0

• How to turn continuous action into discrete action

  #54 opened 4 years ago by Sexu121
  0

• TypeError: must be str, not NoneType

  #52 opened 4 years ago by CHH3213
  0

• reward is too large

  #51 opened 4 years ago by Sherry-97
  0

• ImportError: cannot import name 'prng' when run train.py

  #50 opened 4 years ago by silkyrose
  2

• The sample function in distribution is implementation of Gumbel-softmax, I added it to my code, now it helps to speed up stabilize the training, but my speaker still can not tell the different landmarks.

  #48 opened 4 years ago by tanxiangtj
  0

• Episode in cooperative navigation env

  #47 opened 4 years ago by kargarisaac
  0

• question about p_reg in p_train

  #46 opened 4 years ago by yeshenpy
  0

• Hello! I encountered some problems while running the train.py file under the MADDPG file and would like to seek your help.

  #36 opened 5 years ago by dcy0324
  1

• Typo in train.py

  #44 opened 4 years ago by opt12
  0

• Question regarding the replay buffers and the Critic networks. (duplicates in the state)

  #43 opened 4 years ago by opt12
  0

• run code

  #39 opened 4 years ago by xxd819240366
  1

• Spark

  #41 opened 4 years ago by diemanalytics-ewd
  0

• Error when setting display to true

  #31 opened 5 years ago by njfdiem
  3

• Can someone tell me why agents go beyond bounds when testing?

  #37 opened 5 years ago by glong1997
  0

• The result is not that ideal like the paper showed

  #23 opened 6 years ago by Jarvis-K
  3

• Having trouble with import maddpg

  #22 opened 6 years ago by ishanivyas
  1

• TypeError: must be str, not NoneType . run train.py

  #29 opened 5 years ago by SHYang1210
  2

• Cumulative rewards are not promoted when use MADDPG

  #26 opened 5 years ago by jhcknzzm
  0

• Please add a description to this repo

  #21 opened 6 years ago by clintonyeb
  0

• Calculating Success Rate for Physical Deception

  #20 opened 6 years ago by ZishunYu
  1

• Q divergence

  #19 opened 6 years ago by rbrigden
  0