Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Offline Multi-agent Reinforcement Learning on Warehouse Small (11x20)

5.97Mean Performance (N=2)

AlberDICE

3.55724.18364.815.4364Nov 3, 2023
Updated 1mo ago

Evaluation Results

MethodLinks
2023.11
5.978.189.65
2023.11
5.547.888.9
2023.11
5.437.938.87
2023.11
4.847.688.47
2023.11
4.47.128.41
2023.11
3.656.857.85