Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
RNN-based cooperative multi-agent verification on BoxPushing (BP) 20x20 environment
Loading...
1.51
Avg Violation Rate
RNN-ProVe
1.5012
1.5606
1.62
1.6794
May 14, 2026
Avg Violation Rate
Verification Success Rate (1 - δ)
Error Tolerance (ϵ)
Time (s)
Updated 19d ago
Evaluation Results
Method
Method
Links
Avg Violation Rate
Verification Success Rate (1 - δ)
Error Tolerance (ϵ)
Time (s)
RNN-ProVe
Env size=20×20, GRU si...
2026.05
1.51
99
2.69
0.014
RNN-ProVe
Env size=20×20, GRU si...
2026.05
1.73
99
2.12
0.0476
Feedback
Search any
task
Search any
task