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

Reinforcement Learning on Pusher

142Average Returns

Multi-task

-1,135.432-803.791-472.15-140.509Sep 25, 2020Aug 26, 2021Jul 27, 2022Jun 28, 2023May 28, 2024Apr 28, 2025Mar 30, 2026
Updated 7d ago

Evaluation Results

MethodLinks
2020.09
142
2020.09
99
2020.09
87
2020.09
40
2026.03
39.88
2026.03
32.41
2026.03
27.23
2026.03
25.5
2026.03
25.5
2020.09
7
2020.09
0
2026.01
-408.2
2026.01
-433.6
2026.01
-441
2026.01
-568.3
2026.01
-1,086.3