Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Multi-Agent Reinforcement Learning on TREA rdist

32,421Mean Episodic Reward

MADDPG

-34,718.28-17,287.89142.517,572.89Oct 14, 2022
Updated 4d ago

Evaluation Results

MethodLinks
2022.10
32,421
2022.10
31,878
2022.10
29,193
2022.10
27,100
2022.10
20,437
2022.10
17,306
2022.10
15,436
2022.10
14,473
2022.10
14,364
2022.10
14,249
2022.10
9,627
2022.10
8,342
2022.10
2,742
2022.10
2,712
2022.10
2,567
2022.10
2,384
2022.10
1,776
2022.10
1,708
2022.10
-427
2022.10
-447
2022.10
-449
2022.10
-484
2022.10
-513
2022.10
-691
2022.10
-889
2022.10
-2,733
2022.10
-2,745
2022.10
-2,824
2022.10
-2,956
2022.10
-3,505
2022.10
-3,553
2022.10
-3,741
2022.10
-5,092
2022.10
-5,306
2022.10
-5,340
2022.10
-5,515
2022.10
-5,847
2022.10
-6,912
2022.10
-8,727
2022.10
-8,897
2022.10
-17,986
2022.10
-32,136