List your company

ResearchFormerly WizWand

DMC

Benchmarks

TaskDatasetSOTA resultTrendResults

Continual Reinforcement Learning

DMC6 (Continual)

1.04Normalized Score

24

Reinforcement Learning

DMC Hard

9.41Normalized Mean Return

18

Reinforcement Learning

DMC PointMass

944.5Top Left Score

13

Reinforcement Learning

DMC Quadruped

589.9Run Score

13

Reinforcement Learning

DMC Walker

961.5Walk Score

13

Reinforcement Learning

DMC Cheetah

338.8Run Score

13

Continuous Control

DMC Easy

584Acrobot Swingup Return

9

Continuous Control

DMC (DeepMind Control Suite)

5495th Percentile

8

Code Generation

DMC

73.4PASS@1

8

DMC Dog-run (test)

232.6Average Return

8

DMC Dog-walk (test)

788.7Average Return

8

DMC Dog-stand (test)

879.2Average Return

8

DMC Dog-trot (test)

585.4Average Return

8

DMC Humanoid-walk (test)

226.5Average Return

8

Reinforcement Learning

DMC Walker-run

728.49Normalized AUC

8

Reinforcement Learning

DMC Quadruped-run

717.24Normalized AUC

8

Reinforcement Learning

DMC Hopper-hop

313.78Normalized AUC

8

Reinforcement Learning

DMC Cheetah-run

721.85Normalized AUC

8

Continuous Control (Offline RL)

DMC Cheetah Run → Cheetah Nopaw v1 (offline)

493Mean Reward

8

Continuous Control (Offline RL)

DMC Cheetah Run → Cheetah Uphill v1 (offline)

225Mean Reward

8

Continuous Control (Offline RL)

DMC Cheetah Run → Cheetah Downhill v1 (offline)

745Mean Reward

8

Continuous Control (Offline RL)

DMC Walker Walk → Walker Nofoot v1 (offline)

460Mean Reward

8

Continuous Control (Offline RL)

DMC Walker Walk → Walker Uphill v1 (offline)

407Mean Reward

8

Continuous Control (Offline RL)

DMC Walker Walk → Walker Downhill v1 (offline)

629Mean Reward

8

Continuous Control

DMC Dog

97.4Dog Stand IQM

7