List your company
ResearchFormerly WizWand

Reinforcement Learning on MuJoCo Swimmer v4

271Normalized PerformanceAD-SAC
59.88114.69169.5224.31May 23, 2024
Updated 8mo ago

Evaluation results

MethodLinks
AD-SACDelays=50, Global steps=1M2024.05271
AD-SACDelays=25, Global steps=1M2024.05252
VDPODelays=50, Global steps=1M2024.05242
VDPODelays=25, Global steps=1M2024.05235
VDPODelays=5, Global steps=1M2024.05230
BPQLDelays=50, Global steps=1M2024.05223
AD-SACDelays=5, Global steps=1M2024.05182
BPQLDelays=25, Global steps=1M2024.05136
DC/ACDelays=5, Global steps=1M2024.05111
DIDADelays=5, Global steps=1M2024.05105
BPQLDelays=5, Global steps=1M2024.0597
DIDADelays=25, Global steps=1M2024.0593
A-SACDelays=5, Global steps=1M2024.0588
DIDADelays=50, Global steps=1M2024.0587
DC/ACDelays=25, Global steps=1M2024.0578
A-SACDelays=25, Global steps=1M2024.0572
A-SACDelays=50, Global steps=1M2024.0569
DC/ACDelays=50, Global steps=1M2024.0568