List your company

ResearchFormerly WizWand

InvDoublePend

Benchmarks

TaskDatasetSOTA resultTrendResults

Reinforcement Learning

InvDoublePend

2,000,000Episodes Run

3

Meta-Reinforcement Learning

InvDoublePend params

39FLOPs (k)

3

Reinforcement Learning

InvDoublePend standard (test)

15Episode Length

2

Interpretability Evaluation

InvDoublePend

5Interpretability Score

2