Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-Agent Reinforcement Learning on MAMuJoCo Walker2d 6x1 (test)
Loading...
1,116.75
Average Episodic Return
Sim2O
-37.8476
261.9037
561.655
861.4063
Feb 13, 2026
Mar 6, 2026
Mar 27, 2026
Apr 17, 2026
May 8, 2026
May 29, 2026
Jun 19, 2026
Average Episodic Return
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Episodic Return
Sim2O
Steps=1 million
2026.06
1,116.75
PROTO-MA
Steps=1 million
2026.06
1,062.81
PEX-MA
Steps=1 million
2026.06
1,017.93
RLPD-MA
Steps=1 million
2026.06
884.7
AWAC-MA
Steps=1 million
2026.06
872.62
MMSA
2026.02
28.56
QMIX
2026.02
23.33
VDN
2026.02
18.72
IQL
2026.02
18.61
SMMAE
2026.02
12.16
QMIX-CIA
2026.02
10.86
MASER
2026.02
7.4
QPLEX-CIA
2026.02
6.56
Feedback
Search any
task
Search any
task