List your company

ResearchFormerly WizWand

Lunar Lander

Benchmarks

TaskDatasetSOTA resultTrendResults

Lunar Lander (test)

255.57Average Reward

31

Reinforcement Learning

Lunar Lander POMDP

56.09Performance Score

30

Lunar Lander

78.641Return

15

Imitation Learning

Lunar Lander v2 (test)

107.42Optimality (%)

15

Simulator Benchmark Optimization

Lunar Lander

-12.82Median Performance

9

Multi-Objective Reinforcement Learning

Lunar Lander 4d

1.24Hypervolume (HV)

8

Reinforcement Learning

Lunar Lander (test)

84.6Normalized Win Score (NWS)

6

Reinforcement Learning

Lunar Lander (Best split)

1.098Normalized Win Score (NWS)

6

Reinforcement Learning

Lunar Lander (train)

1.09Normalized Win Score (NWS)

6

MCTS Aggregation Strategy Evaluation

Lunar Lander

83.33MRR

6

Lunar Lander modified (Laggy Pilot)

100Success Rate

6

Lunar Lander modified per Yoneda et al. (Noisy Pilot)

83Success Rate

6

Lunar Lander modified (Expert Pilot)

100Success Rate

6

Lunar Lander (train)

1.09Average Reward

5

Classic Control

Lunar Lander OpenAI Gym (evaluation)

163.5Mean Score

5

Reinforcement Learning

Lunar Lander large state space (test)

314.03Average Performance

4

Lunar Lander Control

Lunar Lander

0.46Success Rate

4

Lunar Lander control

Lunar Lander

256.29Average Collected Reward (Mean)

3

Preference Learning

Lunar Lander Simulated

93.3Alignment

3

Human-in-the-loop Control

Lunar Lander

91.7Success Rate

3