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

AD Trigger threshold control on Monte Carlo (MC) (held-out 20%)

0.3MAE

GFPO-F

Updated 1mo ago

Evaluation Results

Method	Links
GFPO-F 2026.06		0.3	0.7	100	95.442	27.926	95.442	27.926
L-GRPO 2026.06		1	2.2	100	95.369	27.764	95.369	27.764
DQN 2026.06		1.1	2.3	99.3	95.352	27.717	95.357	27.739
PPO 2026.06		1.1	2.2	100	95.353	27.726	95.353	27.726
ADT 2026.06		1.1	2.2	100	95.353	27.726	95.353	27.726
CPO 2026.06		1.1	2.2	100	95.353	27.726	95.353	27.726
GRPO 2026.06		1.3	2.5	95.8	95.347	27.733	95.356	27.74
DQN-F 2026.06		1.6	3	84.7	95.543	28.185	95.474	27.948
GFPO-FR 2026.06		1.9	2.4	97.9	95.842	28.875	95.842	28.868
PID 2026.06		2	5.1	72.9	95.233	27.298	94.99	26.287
DSPOT 2026.06		2.2	6.1	66.7	94.992	26.767	94.867	26.05
Constant 2026.06		4.2	13.1	47.9	94.279	25.404	94.758	25.285