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

Inverted cart-pole balancing

0.0093Violation Rate (Last 100 steps)

PPO-L

Updated 27d ago

Evaluation Results

Method	Links
PPO-L 2026.06		0.0093	0.0094	597.43	597.43	-
PPO-EAL-m 2026.06		0.0099	0.0099	597.68	597.7	-
PPO-EAL 2026.06		0.01	0.0099	597.22	597.15	-
P3O 2026.06		0.011	0.011	595.09	595.06	-
PP0 2026.06		0.013	0.014	596.37	596.34	-
PP0-AL 2026.06		0.026	0.034	596.41	596.59	-