List your company

ResearchFormerly WizWand

MPE

Benchmarks

TaskDatasetSOTA resultTrendResults

Multi-agent Reinforcement Learning

MPE Cooperative Navigation (CN) v1 (Expert)

126.3Normalized Score

19

Multi-Agent Reinforcement Learning

MPE Speaker-Listener

27.9Return

17

Multi-Agent Reinforcement Learning (Predator-Prey)

MPE PP_9/3

802.5Average Cumulative Reward

16

Multi-Agent Reinforcement Learning (Predator-Prey)

MPE PP_6/2

685.5Average Cumulative Reward

16

Multi-Agent Reinforcement Learning (Predator-Prey)

MPE PP_3/1

202.9Average Cumulative Reward

16

Multi-agent Offline Reinforcement Learning

MPE CN (Medium-replay)

95.4Score

16

Multi-agent Offline Reinforcement Learning

MPE CN (Random)

88.3Score

16

Multi-Agent Reinforcement Learning

MPE Predator Prey (Random)

208.7Mean Episode Return

15

Adversarial Attack

MPE spread

-546.99Reward Score

12

Multi-Agent Reinforcement Learning

MPE Adversary

19.1Return

11

Multi-Agent Reinforcement Learning

MPE Simple Spread

-46Return

11

Multi-agent Reinforcement Learning

MPE Predator-prey (PP) v1 (Expert)

118.2Normalized Score

10

Multi-agent Reinforcement Learning

MPE Predator-prey (PP) v1 (Med-Rep)

71.1Normalized Score

10

MPE Random

141.1Normalized Score

9

MPE Expert

163.9Normalized Score

9

MPE Random

133.9Normalized Score

9

MPE Medium

137.1Normalized Score

9

MPE Expert

161.4Normalized Score

9

Cooperative Navigation

MPE Random

69.8Normalized Score

9

Cooperative Navigation

MPE Medium

70.1Normalized Score

9

Multi-Agent Reinforcement Learning

MPE Predator Prey (Medium Expert)

184.4Mean Episode Return

8

Offline Multi-Agent Reinforcement Learning

MPE World (Random)

94.3Average Normalized Score

8

Multi-agent Reinforcement Learning

MPE Simple-World (Random)

15.8Average Normalized Score

6

Multi-agent Reinforcement Learning

MPE Simple-World Medium-Reply

50.9Average Normalized Score

6

Multi-Agent Reinforcement Learning

MPE Adversary (test)

62.9Final Test Return

6