List your company

ResearchFormerly WizWand

MountainCar

Benchmarks

TaskDatasetSOTA resultTrendResults

Reinforcement Learning

MountainCar (Pure)

-44.6Avg Reward (gamma=0.01)

30

Classic Control

MountainCar v1.0 (Drift II)

100Success Rate

27

Classic Control

MountainCar v1.0 (Drift I)

100Success Rate

27

Continuous Control

MountainCar Source

100Success Rate

27

Reinforcement Learning

MountainCar

199.99Avg Episode Reward

25

Classic Discrete Control

MountainCar v0

200Mean Episodic Return

18

Classic Control

MountainCar Source

100Success Rate

18

Continuous Control

MountainCar Drift II - Dynamics Shift

100Success Rate

18

Continuous Control

MountainCar Drift I - Dynamics Shift

100Success Rate

18

Reinforcement Learning

MountainCar

200Maximum Return

14

Continuous Control

MountainCar Explicit Structural Drift II

100Success Rate (Source)

14

Reinforcement Learning

MountainCar

1.4Training Time (min)

13

Reinforcement Learning

MountainCar v0 (test)

-101.72Total Reward

10

Reinforcement Learning

MountainCar (Random)

-45Avg Reward (gamma=0.01)

10

Dynamics Control

MountainCar Dynamics Explicit structural drift (Drift I)

100Success Rate

9

Classic Control

MountainCar Source v1.0

0Success Rate

9

Reinforcement Learning

MountainCar gravity=0.035

-210.6Policy Value

8

Reinforcement Learning

MountainCar gravity=0.025

-189.4Score

8

Reinforcement Learning

MountainCar gravity=0.01

-44.79Policy Value

8

Reinforcement Learning

MountainCar v0

199.99Cumulative Reward

7

Continuous Control

MountainCar

98.74Average Return

7

Reinforcement Learning Surrogate Modeling

MountainCar (MC) (test)

99Reward Ratio

4

Reinforcement Learning

MountainCar

10.6Average Decisions

3

Continuous Control

MountainCar

9.08Action Repetition

3

Reinforcement Learning

MountainCar

2,000,000Episodes

3