List your company

ResearchFormerly WizWand

ExORL

Benchmarks

TaskDatasetSOTA resultTrendResults

Zero-shot Reinforcement Learning

ExORL RND (Quadruped environment) v1 (test)

758Jump Success

12

Zero-shot Reinforcement Learning

ExORL RND Walker environment v1 (test)

644Flip

12

Offline Reinforcement Learning

ExORL

104.7Cheetah Run Score

9

ExORL Jaco Zero-shot RND

48Reach Top Left

8

ExORL Cheetah Zero-shot RND

805Walk Score

8

Zero-shot Reinforcement Learning

ExORL APS (Jaco environment) v1 (test)

88Reach Bottom Left

8

Zero-shot Reinforcement Learning

ExORL APS Cheetah environment v1 (test)

383Run Backward

8

Unsupervised Reinforcement Learning

ExORL jaco (4 tasks) zero-shot

23Average Return

6

Unsupervised Reinforcement Learning

ExORL quadruped zero-shot

645Average Return

6

Unsupervised Reinforcement Learning

ExORL cheetah (4 tasks) zero-shot

378Average Return

6

Unsupervised Reinforcement Learning

ExORL walker (4 tasks) zero-shot

619Average Return

6

Zero-shot Reinforcement Learning

ExORL APS Quadruped environment v1 (test)

757Jump Score

4

Zero-shot Reinforcement Learning

ExORL APS Walker environment v1 (test)

573Flip Count

4