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

Classic Discrete Control on CartPole v1

495Mean Episodic Return

FP16-PPO

5.16132.33259.5386.67Apr 27, 2026May 2, 2026May 7, 2026May 12, 2026May 17, 2026May 22, 2026May 27, 2026
Updated 5d ago

Evaluation Results

MethodLinks
2026.04
495-
2026.04
492-
2026.04
489-
2026.04
487-
2026.04
47696.2
2026.05
466.3-
2026.05
458.5-
2026.05
373.2-
2026.05
351.1-
2026.05
230.8-
2026.05
204.4-
2026.05
169.9-
2026.05
149.4-
2026.05
139.1-
2026.05
120.8-
2026.05
112.6-
2026.05
26.1-
2026.05
24-