List your company
ResearchFormerly WizWand

Continuous Control on MuJoCo Ant v4

8,509Average ReturnTD7
-587.6721,773.9644,135.66,497.236Sep 24, 2025Nov 2, 2025Dec 12, 2025Jan 21, 2026Mar 1, 2026Apr 10, 2026May 20, 2026
Updated 5mo ago

Evaluation results

MethodLinks
TD7Environment Steps=1M, Number of Random Seeds=102026.058,509——
DR.QEnvironment Steps=1M, Number of Random Seeds=102026.058,138——
SMFPNFE=12026.057,518.3——
SimbaV2Environment Steps=1M, Number of Random Seeds=102026.057,429——
TD3+OFEEnvironment Steps=1M, Number of Random Seeds=102026.057,398——
DIMENFE=162026.057,103.6——
BROEnvironment Steps=1M, Number of Random Seeds=102026.057,027——
CrossQEnvironment Steps=1M, Number of Random Seeds=102026.056,980——
MR.QEnvironment Steps=1M, Number of Random Seeds=102026.056,901——
FoGEnvironment Steps=1M, Number of Random Seeds=102026.056,761——
TD32025.096,542.34——
FQL2025.096,176.6——
DroQEnvironment Steps=1M, Number of Random Seeds=102026.055,965——
DPMDNFE=202026.055,931.8——
SimBaEnvironment Steps=1M, Number of Random Seeds=102026.055,882——
SAC Flow-GNFE=42026.055,847.1——
SAC Flow-TNFE=42026.055,787.6——
FPMD-MNFE=12026.055,762.4——
FPMD-RNFE=12026.055,756.2——
MaxEntDPNFE=202026.055,717.9——
DIPONFE=202026.055,665.9——
MEOW2025.095,635.11——
ILC-SANAlgorithm=TD3, Simulation time steps=5, Neuron type=CLIF spiking neurons2025.095,584——
SACNFE=12026.055,530.6——
FlowRLNFE=12026.055,513.3——
CaRe-BNAlgorithm=TD3, Simulation time steps=5, Neuron type=CLIF spiking neurons2025.095,373——
REDQEnvironment Steps=1M, Number of Random Seeds=102026.055,314——
MDC-SANAlgorithm=TD3, Simulation time steps=5, Neuron type=CLIF spiking neurons2025.094,800——
ANNAlgorithm=TD32025.094,770——
TDMPC2Environment Steps=1M, Number of Random Seeds=102026.054,751——
pop-SANAlgorithm=TD3, Simulation time steps=5, Neuron type=CLIF spiking neurons2025.094,590——
TD3NFE=12026.054,583.8——
TEBNAlgorithm=TD3, Simulation time steps=5, Neuron type=CLIF spiking neurons2025.094,408——
tdBNAlgorithm=TD3, Simulation time steps=5, Neuron type=CLIF spiking neurons2025.094,403——
TABNAlgorithm=TD3, Simulation time steps=5, Neuron type=CLIF spiking neurons2025.094,382——
BNTTAlgorithm=TD3, Simulation time steps=5, Neuron type=CLIF spiking neurons2025.094,379——
QSMNFE=202026.054,206.4——
QVPONFE=202026.054,040.1——
TQCEnvironment Steps=1M, Number of Random Seeds=102026.053,582——
ANN-SNNAlgorithm=TD3, Simulation time steps=5, Neuron type=CLIF spiking neurons2025.093,550——
SAC2025.093,098.49——
PPONFE=12026.052,781.9——
SPONFE=12026.052,100.2——
DreamerV3Environment Steps=1M, Number of Random Seeds=102026.051,947——
PPOEnvironment Steps=1M, Number of Random Seeds=102026.051,584——
DDPG2025.09-237.8——
A-SACDelays=5, Global steps=1M2024.05—0.18—
A-SACDelays=25, Global steps=1M2024.05—0.07—
A-SACDelays=50, Global steps=1M2024.05—0.02—
AD-SACDelays=5, Global steps=1M2024.05—0.72—
AD-SACDelays=25, Global steps=1M2024.05—0.66—
AD-SACDelays=50, Global steps=1M2024.05—0.48—
BPOEvaluation Protocol=Converged2026.04——4,871.4
BPQLDelays=5, Global steps=1M2024.05—0.96—
BPQLDelays=25, Global steps=1M2024.05—0.57—
BPQLDelays=50, Global steps=1M2024.05—0.38—
CQL2026.02—-13.8—
DC/ACDelays=5, Global steps=1M2024.05—0.25—
DC/ACDelays=25, Global steps=1M2024.05—0.19—
DC/ACDelays=50, Global steps=1M2024.05—0.19—
DIDADelays=5, Global steps=1M2024.05—0.89—
DIDADelays=25, Global steps=1M2024.05—0.29—
DIDADelays=50, Global steps=1M2024.05—0.19—
Flex-f-DICE2026.02—136—
Flex-f-Q2026.02—123.1—
IQL2026.02—113.8—
Opti-DICE2026.02—126—
PPOEvaluation Protocol=Converged2026.04——4,230.1
SACEvaluation Protocol=Converged2026.04——6,161.8
TD3BC2026.02—53.7—
VDPODelays=5, Global steps=1M2024.05—1.11—
VDPODelays=25, Global steps=1M2024.05—0.56—
VDPODelays=50, Global steps=1M2024.05—0.46—