HyperAI超神经

Commonsense Rl On Commonsense Rl

评估指标

Avg #Steps

评测结果

各个模型在此基准测试上的表现结果

比较表格
模型名称Avg #Steps
text-based-rl-agents-with-commonsense15.00 ± 3.29
text-based-rl-agents-with-commonsense15.00 ± 2.00
text-based-rl-agents-with-commonsense49.36 ± 7.50
text-based-rl-agents-with-commonsense43.27 ± 0.70
text-based-rl-agents-with-commonsense49.21 ± 0.58