Lunar Lander
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Control Task | Lunar Lander (test) | Average Reward255.57 | 31 | |
| Reinforcement Learning | Lunar Lander POMDP | Performance Score56.09 | 30 | |
| Planning | Lunar Lander | Return78.641 | 15 | |
| Imitation Learning | Lunar Lander v2 (test) | Optimality (%)107.42 | 15 | |
| Simulator Benchmark Optimization | Lunar Lander | Median Performance-12.82 | 9 | |
| Multi-Objective Reinforcement Learning | Lunar Lander 4d | Hypervolume (HV)1.24 | 8 | |
| Reinforcement Learning | Lunar Lander (test) | Normalized Win Score (NWS)84.6 | 6 | |
| Reinforcement Learning | Lunar Lander (Best split) | Normalized Win Score (NWS)1.098 | 6 | |
| Reinforcement Learning | Lunar Lander (train) | Normalized Win Score (NWS)1.09 | 6 | |
| MCTS Aggregation Strategy Evaluation | Lunar Lander | MRR83.33 | 6 | |
| Lunar Landing | Lunar Lander modified (Laggy Pilot) | Success Rate100 | 6 | |
| Lunar Landing | Lunar Lander modified per Yoneda et al. (Noisy Pilot) | Success Rate83 | 6 | |
| Lunar Landing | Lunar Lander modified (Expert Pilot) | Success Rate100 | 6 | |
| Lunar Lander | Lunar Lander (train) | Average Reward1.09 | 5 | |
| Classic Control | Lunar Lander OpenAI Gym (evaluation) | Mean Score163.5 | 5 | |
| Reinforcement Learning | Lunar Lander large state space (test) | Average Performance314.03 | 4 | |
| Lunar Lander Control | Lunar Lander | Success Rate0.46 | 4 | |
| Lunar Lander control | Lunar Lander | Average Collected Reward (Mean)256.29 | 3 | |
| Preference Learning | Lunar Lander Simulated | Alignment93.3 | 3 | |
| Human-in-the-loop Control | Lunar Lander | Success Rate91.7 | 3 |
Showing 20 of 20 rows