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

Reinforcement Learning on Pong

40Average Reward

Average Human

-0.83049.769820.3730.9702May 29, 2024Sep 24, 2024Jan 20, 2025May 18, 2025Sep 13, 2025Jan 9, 2026May 8, 2026
Updated 22d ago

Evaluation Results

MethodLinks
40
2024.05
19
2024.05
18
2024.05
17
2026.05
2.51
2026.05
1.22
2026.05
1.02
2026.05
0.74