Continuous Control On Simple Humanoid
Metriken
Score
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | Score | Paper Title | Repository |
|---|---|---|---|
| TRPO | 269.7 | Benchmarking Deep Reinforcement Learning for Continuous Control | - |
0 of 1 row(s) selected.