openai/maddpg issues and pull requests

#82 - MADDPG for custom environment

Issue - State: open - Opened by kapilgarg7568 5 months ago

#81 - Transferreg

Pull Request - State: open - Opened by Hasenfus 8 months ago - 1 comment

#80 - python3.5.4已经进行维护。

Issue - State: open - Opened by vducd 8 months ago

#79 - How to save the videos of each 1000th episode ?

Issue - State: open - Opened by longxilong 10 months ago

#78 - Unit yx ma mu ju co

Pull Request - State: open - Opened by Hasenfus 10 months ago

#77 - Update architecture

Pull Request - State: closed - Opened by Boxxfish 12 months ago

#76 - ModuleNotFoundError: No module named 'maddpg.common'

Issue - State: open - Opened by yanmmmm about 1 year ago - 1 comment

#75 - 测试Pull Request

Pull Request - State: open - Opened by tetris-4444 about 1 year ago

#74 - 测试Pull Request

Pull Request - State: open - Opened by tetris-4444 about 1 year ago

#72 - Rgb array

Pull Request - State: closed - Opened by jin749 over 1 year ago - 1 comment

#71 - DDPG action space vs multi-agent particle environment action space

Issue - State: open - Opened by medhijk about 2 years ago

#70 - Loading previous state...

Issue - State: open - Opened by yanwaiwai over 2 years ago - 2 comments

#69 - A issue about the saving the model in train.py

Issue - State: open - Opened by chengdusunny over 2 years ago

#68 - A question about maddpg.py

Issue - State: open - Opened by chengdusunny over 2 years ago

#67 - Training EVERY step, not every 100

Issue - State: open - Opened by eflopez1 about 3 years ago - 1 comment

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

Issue - State: open - Opened by ScorpioPeng about 3 years ago - 2 comments

#65 - Question about the way how to update actor

Issue - State: open - Opened by choasLC about 3 years ago - 1 comment

#64 - How to run ddpg

Issue - State: open - Opened by EvaluationResearch over 3 years ago

#63 - All scenario will fail but except scenario simple

Issue - State: closed - Opened by EvaluationResearch over 3 years ago - 1 comment

#62 - Update train.py

Pull Request - State: closed - Opened by duanzy18 over 3 years ago - 1 comment

#61 - change '-' in arguments' name to '_'

Pull Request - State: closed - Opened by duanzy18 over 3 years ago

#60 - Is policy ensambles implemented in this repository?

Issue - State: open - Opened by 2015211289 over 3 years ago

#59 - ../../..

Issue - State: open - Opened by devarani10 over 3 years ago

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

Issue - State: closed - Opened by dr-smgad over 3 years ago

#57 - how to evaluate maddpg?

Issue - State: open - Opened by Xinlei-Ren over 3 years ago

#56 - how to evaluate maddpg?

Issue - State: open - Opened by Xinlei-Ren over 3 years ago

#55 - How to normalize the data in table of Appendix to obtain Figure 3 in paper?

Issue - State: open - Opened by flammingRaven almost 4 years ago - 1 comment

#54 - How to turn continuous action into discrete action

Issue - State: open - Opened by Sexu121 almost 4 years ago - 1 comment

#53 - How can I use DDPG to train it?

Issue - State: closed - Opened by CHH3213 about 4 years ago

#52 - TypeError: must be str, not NoneType

Issue - State: closed - Opened by CHH3213 about 4 years ago

#51 - reward is too large

Issue - State: open - Opened by Sherry-97 about 4 years ago

#50 - ImportError: cannot import name 'prng' when run train.py

Issue - State: closed - Opened by silkyrose about 4 years ago - 2 comments

#49 - I have train it success but how to run? How to see the visible answer?

Issue - State: open - Opened by zhijiejia over 4 years ago - 2 comments

#48 - 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.

Issue - State: closed - Opened by tanxiangtj over 4 years ago

#47 - Episode in cooperative navigation env

Issue - State: open - Opened by kargarisaac over 4 years ago

#46 - question about p_reg in p_train

Issue - State: open - Opened by yeshenpy over 4 years ago

#45 - Trying to set the random seeds, any idea how?

Issue - State: open - Opened by hossein-haeri over 4 years ago - 1 comment

#44 - Typo in train.py

Issue - State: open - Opened by opt12 over 4 years ago

#43 - Question regarding the replay buffers and the Critic networks. (duplicates in the state)

Issue - State: open - Opened by opt12 over 4 years ago

#42 - urls to the code of policy ensemble and estimate

Pull Request - State: closed - Opened by jxwuyi over 4 years ago

#41 - Spark

Issue - State: open - Opened by diemanalytics-ewd over 4 years ago

#41 - Spark

Issue - State: open - Opened by diemanalytics-ewd over 4 years ago

#40 - SoftMultiCategoricalPd

Issue - State: open - Opened by sandeepnRES almost 5 years ago - 1 comment

#39 - run code

Issue - State: open - Opened by lionel-xie almost 5 years ago - 1 comment

#39 - run code

Issue - State: open - Opened by lionel-xie almost 5 years ago - 1 comment

#38 - Animate

Pull Request - State: closed - Opened by RavenPillmann almost 5 years ago

#37 - Can someone tell me why agents go beyond bounds when testing?

Issue - State: open - Opened by glong1997 almost 5 years ago - 1 comment

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

Issue - State: open - Opened by dcy0324 almost 5 years ago - 1 comment

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

Issue - State: open - Opened by dcy0324 almost 5 years ago - 1 comment

#35 - what's benchmark used for?

Issue - State: open - Opened by KK666-AI almost 5 years ago - 1 comment

#34 - The code does not converged

Issue - State: open - Opened by sjq19960802 over 5 years ago - 1 comment

#33 - There is no provision to run ddpg.

Issue - State: open - Opened by frenzytejask98 over 5 years ago - 3 comments

#32 - Two problem about update function

Issue - State: open - Opened by YuanyeMa over 5 years ago - 5 comments

#31 - Error when setting display to true

Issue - State: open - Opened by njfdiem over 5 years ago - 3 comments

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

Issue - State: open - Opened by marwanihab over 5 years ago - 6 comments

#29 - TypeError: must be str, not NoneType . run train.py

Issue - State: closed - Opened by SHYang1210 over 5 years ago - 2 comments

#28 - Nontype flaw in "train.py", line 182

Issue - State: open - Opened by DailinH almost 6 years ago - 3 comments

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

Issue - State: closed - Opened by alexanderkell almost 6 years ago - 2 comments

#26 - Cumulative rewards are not promoted when use MADDPG

Issue - State: open - Opened by jhcknzzm almost 6 years ago

#25 - use tf.layers and add gpu_options.allow_growth=True

Pull Request - State: closed - Opened by GoingMyWay almost 6 years ago

#24 - update README with repo status

Pull Request - State: closed - Opened by christopherhesse almost 6 years ago

#23 - The result is not that ideal like the paper showed

Issue - State: open - Opened by Jarvis-K about 6 years ago - 3 comments

#22 - Having trouble with import maddpg

Issue - State: open - Opened by ishanivyas about 6 years ago - 1 comment

#21 - Please add a description to this repo

Issue - State: open - Opened by clintonyeb over 6 years ago

#20 - Calculating Success Rate for Physical Deception

Issue - State: closed - Opened by ZishunYu over 6 years ago - 1 comment

#19 - Q divergence

Issue - State: open - Opened by rbrigden over 6 years ago

#18 - How or why the gaussian distribution contributes to the training?

Issue - State: open - Opened by Chen-Joe-ZY over 6 years ago - 4 comments

#17 - Import Errors

Issue - State: closed - Opened by murtazarang over 6 years ago - 6 comments

#16 - How maddpg update actor?

Issue - State: closed - Opened by newbieyxy over 6 years ago

#15 - Error in scenario simple_reference with gym.spaces.MultiDiscrete

Issue - State: closed - Opened by hcch0912 over 6 years ago - 1 comment

#14 - displaying agent behaviors on the screen

Issue - State: closed - Opened by williamyuanv0 over 6 years ago - 1 comment

#13 - When I run train.py,it shows "TypeError: Can't convert 'NoneType' object to str implicitly".

Issue - State: closed - Opened by seahawkk over 6 years ago - 4 comments

#12 - Cannot reproduce experiment results

Issue - State: closed - Opened by arbaazkhan2 over 6 years ago - 3 comments

#11 - The reward and action is nan ?

Issue - State: closed - Opened by yexm-ze over 6 years ago - 3 comments

#10 - How can i use it for "simple_world_comm" in MPE? ---- "AssertionError: nvec should be a 1d array (or list) of ints"

Issue - State: closed - Opened by zimoqingfeng over 6 years ago - 1 comment

#9 - action exploration & Gumbel-Softmax

Issue - State: open - Opened by djbitbyte over 6 years ago - 9 comments

#8 - It seems that you don't use "Policy ensembles" and "Inferring policies of other agent" in this code?

Issue - State: closed - Opened by pengzhenghao over 6 years ago - 2 comments

#7 - It seems that the training is decentralized?

Issue - State: closed - Opened by pengzhenghao over 6 years ago - 1 comment

#6 - Running train.py doesn't seem to work

Issue - State: closed - Opened by suryabhupa over 6 years ago - 5 comments

#5 - when I run train.py,it shows "module 'tensorflow' has no attribute 'float32'"

Issue - State: closed - Opened by williamyuanv0 over 6 years ago - 8 comments

#4 - add multiagent-particle-envs to PYTHONPATH

Issue - State: closed - Opened by djbitbyte over 6 years ago - 4 comments

#3 - fix some miss

Pull Request - State: closed - Opened by wwxFromTju over 6 years ago

#2 - rnn_]cell=None is a Syntax Error in both Python 2 and 3

Issue - State: closed - Opened by cclauss over 6 years ago - 1 comment

#1 - Remove pycache and add gitignore

Pull Request - State: closed - Opened by himanshub16 over 6 years ago

GitHub / openai/maddpg issues and pull requests