Pendulum

Benchmarks

Task Name	Dataset Name	SOTA Result
Reinforcement Learning Control	Pendulum v1	Mean Score1,378.78	40
Reinforcement Learning	Pendulum	Avg Episode Reward-145.49	26
State Estimation	Pendulum	MAE0.7	21
Reinforcement Learning	Pendulum v1 (test)	Average Return-164.82	16
Regression	Pendulum (test)	MSE0.0034	14
Continuous Control	Pendulum	Robustness Gap0.72	12
Rollout prediction	Pendulum	Rollout MSE1.05	12
Continuous Control	Pendulum	Median Samples5.6	12
Continuous Control	Pendulum v1	Average Cumulative Reward-150.8	11
Regression	Pendulum	MSE3.32	11
Parameter Estimation	Pendulum 90cm	Length (m)1.07	9
Continuous Control	Pendulum Nonmarkov v1 (test)	AUC@T-556.9	9
Control	Pendulum v0	Median Samples21	9
Transition model estimation	Pendulum discretized n = 10^5	Failure Rate0	8
Image Interpolation	Pendulum (test)	MSE1	8
Reinforcement Learning	Pendulum classical control (1M steps)	Return-133.42	8
Dynamical Identification	Pendulum Numerical	AUC99	7
Robotic Control	Pendulum v1	Local Optima Escape Rate89.2	7
Counterfactual Generation	Pendulum (test)	MAE (Pendulum (p) \| do(p))0.013	6
Reinforcement Learning	Pendulum	Steps (Mean)80,240	6
Reinforcement Learning	Pendulum PD-C (test)	Cumulative Reward854	6
Continuous Control (Negative Reward)	Pendulum Pybullet	Mean Return9,124.6	6
Continuous Control (Positive Reward)	Pendulum Pybullet	Return9,043.3	6
Continuous Control (Negative Reward)	Pendulum Mujoco	Mean Return8,132.1	6
Continuous Control (Positive Reward)	Pendulum Mujoco	Return9,358.4	6

Showing 25 of 70 rows