Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
RNN-based cooperative multi-agent verification on BoxPushing (BP) 10x10 environment
Loading...
1.15
Average Violation Rate
RNN-ProVe
1.1488
1.1569
1.165
1.1731
May 14, 2026
Average Violation Rate
Success Rate (1 - δ)
Epsilon Error Rate (ϵ)
Execution Time (s)
Updated 19d ago
Evaluation Results
Method
Method
Links
Average Violation Rate
Success Rate (1 - δ)
Epsilon Error Rate (ϵ)
Execution Time (s)
RNN-ProVe
Env size=10×10, GRU si...
2026.05
1.15
99
2.45
0.0072
RNN-ProVe
Env size=10×10, GRU si...
2026.05
1.18
99
1.76
0.0179
Feedback
Search any
task
Search any
task