Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Sampling on VMAS
Loading...
34.86
Mean Episodic Reward
CoHetteam
17.128
21.7315
26.335
30.9385
Aug 12, 2024
Mean Episodic Reward
Updated 1mo ago
Evaluation Results
Method
Method
Links
Mean Episodic Reward
CoHetteam
Environment Steps=2×10^5
2024.08
34.86
CoHetself
Environment Steps=2×10^5
2024.08
31.75
IPPO
Environment Steps=2×10^5
2024.08
26.13
HetGPPO
Environment Steps=2×10^5
2024.08
17.81
Feedback
Search any
task
Search any
task