MLGym
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Reinforcement Learning | MLGym Breakout | Reward100 | 7 | |
| Decision Making | MLGym Prisoner's Dilemma | Payoff3 | 7 | |
| Decision Making | MLGym Battle of Sexes | Payoff2 | 7 | |
| Language Modeling | MLGym Language Modeling | Loss3.5 | 7 | |
| Natural Language Inference | MLGym MNLI | Accuracy92.5 | 7 | |
| Tabular Regression | MLGym House Price | R20.99 | 7 |
Showing 6 of 6 rows