Reinforcement Learning on Lunar Lander large state space (test)
314.03Average PerformancePrimitives
Evaluation results
| Method | Links | |
|---|---|---|
| PrimitivesAction set=Primitives, Implementation=Tabular2017.11 | 314.03 | |
| Eigen-OptionsImplementation=Tabular2017.11 | 266.43 | |
| Option-CriticImplementation=Tabular2017.11 | 265.51 | |
| Primitives+MacroAction set=Primitives + Macros, Implementation=Tabular2017.11 | 246.89 |