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

Reinforcement Learning on DeepMind Control Reacher Hard (Convergence)

589.7Steps to 75% Return (k)

Dreamer V3

552.62802.911,053.21,303.49May 15, 2026
Updated 16d ago

Evaluation Results

MethodLinks
2026.05
589.7
2026.05
698.2
2026.05
707
2026.05
804.9
2026.05
827.4
2026.05
967.8
1,196.7
1,516.7