Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reinforcement Learning on DeepMind Control Cartpole Balance Sparse
Loading...
150,700
Steps to 75% Return
Dreamer V3
120,860
322,280
523,700
725,120
May 15, 2026
Steps to 75% Return
Updated 16d ago
Evaluation Results
Method
Method
Links
Steps to 75% Return
Dreamer V3
2026.05
150,700
Mind Dreamer
Horizon=10
2026.05
158,300
Mind Dreamer
Horizon=10
2026.05
166,300
Mind Dreamer
Horizon=5
2026.05
166,700
Dreamer V3
2026.05
170,400
Mind Dreamer
Horizon=15
2026.05
171,300
Mind Dreamer
Horizon=5
2026.05
174,400
Mind Dreamer
Horizon=15
2026.05
178,500
Dreamer V2
2026.05
345,000
Dreamer V2
2026.05
381,700
Plan2Explore
2026.05
896,700
Feedback
Search any
task
Search any
task