Share your thoughts, 1 month free Claude Pro on usSee more

MountainCar

Benchmarks

Task Name	Dataset Name	SOTA Result
Reinforcement Learning	MountainCar (Pure)	Avg Reward (gamma=0.01)-44.6	30
Classic Control	MountainCar v1.0 (Drift II)	Success Rate100	27
Classic Control	MountainCar v1.0 (Drift I)	Success Rate100	27
Continuous Control	MountainCar Source	Success Rate100	27
Classic Control	MountainCar Source	Success Rate100	18
Continuous Control	MountainCar Drift II - Dynamics Shift	Success Rate100	18
Continuous Control	MountainCar Drift I - Dynamics Shift	Success Rate100	18
Continuous Control	MountainCar Explicit Structural Drift II	Success Rate (Source)100	14
Reinforcement Learning	MountainCar	Avg Episode Reward0.9911	14
Reinforcement Learning	MountainCar v0 (test)	Total Reward-101.72	10
Reinforcement Learning	MountainCar (Random)	Avg Reward (gamma=0.01)-45	10
Dynamics Control	MountainCar Dynamics Explicit structural drift (Drift I)	Success Rate100	9
Classic Control	MountainCar Source v1.0	Success Rate0	9
Reinforcement Learning	MountainCar gravity=0.035	Policy Value-210.6	8
Reinforcement Learning	MountainCar gravity=0.025	Score-189.4	8
Reinforcement Learning	MountainCar gravity=0.01	Policy Value-44.79	8
Reinforcement Learning	MountainCar	Maximum Return147.8	5
Reinforcement Learning	MountainCar	Average Decisions10.6	3
Continuous Control	MountainCar	Action Repetition9.08	3
Continuous Control	MountainCar	AUC (Normalized)82	3
Reinforcement Learning	MountainCar	Episodes2,000,000	3
Sensory-motor control	MountainCar Discrete Gymnasium	Mean Best Reward-111.54	2
Sensory-motor control	MountainCar Continuous Gymnasium	Mean Best Reward94.81	2
Closed-loop verification	MountainCar	TNR100	2
Interpretability Evaluation	MountainCar	Interpretability Score5	2

Showing 25 of 26 rows