uoe-agents/epymarl

Issues

• Bugs Finding in action_selector.py

  #75 opened 2 months ago by W-Zhi-Chao
  1

• Support for PettingZoo?

  #12 opened 4 months ago by Phoenix-surgere
  4

• Problems with SMAC and SMACv2

  #74 opened 4 months ago by opocaj92
  5

• AttributeError: Has no attribute 'unit_dim'

  #33 opened 4 months ago by Skylarking
  1

• Unable to install requirements.txt

  #35 opened 4 months ago by lcdbezerra
  6

• Does this library support continuous action spaces?

  #47 opened 4 months ago by 128f
  4

• How could I render the lbf environment?

  #52 opened 4 months ago by issuey
  1

• Unable to install requirements.txt

  #53 opened 4 months ago by xylhal
  5

• Hi, why NonSharedMAC only has one agent? thanks

  #58 opened 4 months ago by restart-again
  1

• Question about MAPPO centralized critic's target network

  #62 opened 4 months ago by Yuxin916
  1

• Recommended torch version?

  #63 opened 4 months ago by LXXXXR
  1

• Adding new environment to ePYMARL

  #64 opened 4 months ago by ay-ka
  1

• SMACv2 and SMAC Lite

  #66 opened 4 months ago by rfali
  1

• Errors in search.py

  #73 opened 4 months ago by opocaj92
  1

• [BUG] Duplicate agent_grad_norm in maddpg_learner.py Needs Removal

  #67 opened 5 months ago by wmn7
  1

• Get stats not being used in parallel runner

  #70 opened 5 months ago by Warry98
  0

• Training code for pretrained adversarial policies

  #65 opened 10 months ago by LXXXXR
  0

• Parameters of MAPPO in different scenarios

  #61 opened a year ago by ZhuohuiZhang
  0

• mpe gym.error

  #28 opened 2 years ago by Bruce-Lan-ZY
  8

• How to load model and visualize results

  #30 opened 2 years ago by darwinharianto
  6

• MADDPG algorithm problem

  #51 opened 2 years ago by abdulghani91
  0

• Question with the implentation of Modules w.r.t different Multi-agent algorithms

  #50 opened 2 years ago by sputnik524
  0

• SMAC environment problem

  #45 opened 2 years ago by abdulghani91
  9

• How to get the Episodic return graph

  #48 opened 2 years ago by FADEAWAY114
  8

• nan while training MAPPO on RWARE

  #32 opened 2 years ago by hughjazzman
  6

• Result with IPPO in SMAC: 2s_vs_1sc

  #21 opened 3 years ago by simsimiSION
  3

• Exploding targets for A2C and task Tag when add_value_last_step: True

  #43 opened 2 years ago by gsavarela
  1

• Are values from Tables 3-7 for task MPE Tag, algorithms MAA2C and MAA2C_NS swapped?

  #44 opened 2 years ago by gsavarela
  0

• Are values from Tables 7-8 for task LBF-15x15-3p-5f and algorithm VDN_NS switched?

  #42 opened 2 years ago by gsavarela
  0

• LBF results with IA2C and MAA2C: Foraging-15x15-4p-5f-v1

  #26 opened 2 years ago by gsavarela
  1

• Gym Videorecorder not working with LBFG environment

  #40 opened 2 years ago by bornexmachina
  0

• Problem with the implementation of MADDPG

  #31 opened 2 years ago by zhang275
  1

• How to render or view gifs?

  #39 opened 2 years ago by atapley
  1

• repeated matrix game

  #37 opened 2 years ago by wenshuaizhao
  2

• why "return" remains constant in my custom environment?

  #38 opened 2 years ago by SaraRezaei
  0

• TypeError: 'Box' object is not iterable, WHY?

  #36 opened 2 years ago by SaraRezaei
  2

• About training the MADDPG in MPE.

  #34 opened 2 years ago by xinyu-site
  0

• Choosing runner: "parallel" in maddpg_ns.yaml causes error.

  #27 opened 2 years ago by xiaobanni
  1

• RWARE with MAPPO training

  #22 opened 2 years ago by miguel-arrf
  3

• Cannot obtain the reported results on MPE:SimpleSpread task

  #29 opened 2 years ago by wenshuaizhao
  2

• Training slows down

  #25 opened 2 years ago by GoingMyWay
  5

• network type configuration

  #24 opened 2 years ago by miguel-arrf
  7

• Did you try to use the true global state as input in LBF?

  #16 opened 3 years ago by GoingMyWay
  2

• Why batch reward standarization works?

  #10 opened 3 years ago by to1a
  1

• Weird, a2c and ppo learner has a target critic network

  #17 opened 3 years ago by Theohhhu
  3

• Evaluate results question

  #20 opened 3 years ago by AlRodA92
  2

• error running example rware/lbforaging

  #18 opened 3 years ago by kinalmehta
  4

• Number of Evaluations between Off-Policy and On-Policy

  #15 opened 3 years ago by AlRodA92
  2

• GPU usage without run.sh

  #13 opened 3 years ago by AlRodA92
  2

• Implementation tricks for different algorithms

  #11 opened 3 years ago by waterhorse1
  2