List your company
ResearchFormerly WizWand

Locomotion on Hopper

100Convergence (%)DAgger
58.469.28090.8Nov 29, 2025
Updated 4mo ago

Evaluation results

MethodLinks
DAggerInitial expert dataset size (M)=1,000, Training steps (T_train)=10,000, K=5, alpha_Hopper=0.952025.11100—3,930,6191,019,895
DAggerInitial expert dataset size (M)=2,000, Training steps (T_train)=10,000, K=5, alpha_Hopper=0.952025.11100—3,728,60110,242,247
DAggerInitial expert dataset size (M)=5,000, Training steps (T_train)=10,000, K=5, alpha_Hopper=0.952025.11100—3,040,87010,249,170
DAggerInitial expert dataset size (M)=10,000, Training steps (T_train)=10,000, K=5, alpha_Hopper=0.952025.11100—3,294,6961,009,159
DAggerInitial expert dataset size (M)=20,000, Training steps (T_train)=10,000, K=5, alpha_Hopper=0.952025.11100—4,576,65710,192,135
EnsembleDAggerInitial expert dataset size (M)=1,000, Training steps (T_train)=10,000, K=5, alpha_Hopper=0.952025.11100—1,969,1788,879,193
EnsembleDAggerInitial expert dataset size (M)=2,000, Training steps (T_train)=10,000, K=5, alpha_Hopper=0.952025.11100—1,839,3188,722,217
EnsembleDAggerInitial expert dataset size (M)=5,000, Training steps (T_train)=10,000, K=5, alpha_Hopper=0.952025.11100—2,043,3248,966,155
EnsembleDAggerInitial expert dataset size (M)=10,000, Training steps (T_train)=10,000, K=5, alpha_Hopper=0.952025.11100—1,990,4468,806,315
EnsembleDAggerInitial expert dataset size (M)=20,000, Training steps (T_train)=10,000, K=5, alpha_Hopper=0.952025.11100—2,804,3208,576,137
ThriftyDAggerInitial expert dataset size (M)=1,000, Training steps (T_train)=10,000, K=5, alpha_Hopper=0.952025.11100—1,514,4872,991,118
ThriftyDAggerInitial expert dataset size (M)=2,000, Training steps (T_train)=10,000, K=5, alpha_Hopper=0.952025.11100—1,100,4032,873,183
ThriftyDAggerInitial expert dataset size (M)=10,000, Training steps (T_train)=10,000, K=5, alpha_Hopper=0.952025.11100—1,566,1342,740,182
CRSAILInitial expert dataset size (M)=1,000, Training steps (T_train)=10,000, K=5, alpha_Hopper=0.952025.11100—1,821,1032,928,298
CRSAILInitial expert dataset size (M)=5,000, Training steps (T_train)=10,000, K=5, alpha_Hopper=0.952025.11100—2,355,2794,038,978
CRSAILInitial expert dataset size (M)=10,000, Training steps (T_train)=10,000, K=5, alpha_Hopper=0.952025.11100—2,694,40857,601,286
CRSAILInitial expert dataset size (M)=20,000, Training steps (T_train)=10,000, K=5, alpha_Hopper=0.952025.11100—2,519,6283,388,702
ThriftyDAggerInitial expert dataset size (M)=5,000, Training steps (T_train)=10,000, K=5, alpha_Hopper=0.952025.1180—1,537,2472,827,164
CRSAILInitial expert dataset size (M)=2,000, Training steps (T_train)=10,000, K=5, alpha_Hopper=0.952025.1180—2,299,3002,578,296
ThriftyDAggerInitial expert dataset size (M)=20,000, Training steps (T_train)=10,000, K=5, alpha_Hopper=0.952025.1160—1,806,487265,043
BC#Preferences=502026.06—456——
BC#Preferences=5002026.06—401——
CPL#Preferences=502026.06—391——
CPL#Preferences=5002026.06—398——
CPL+KL#Preferences=502026.06—451——
CPL+KL#Preferences=5002026.06—405——
IPL#Preferences=502026.06—436——
IPL#Preferences=5002026.06—385——
P-IQL#Preferences=502026.06—397——
P-IQL#Preferences=5002026.06—571——
PAWS (MLP)#Preferences=502026.06—512——
PAWS (MLP)#Preferences=5002026.06—637——
PAWS (Trans.)#Preferences=502026.06—484——
PAWS (Trans.)#Preferences=5002026.06—563——
Pref Trans.#Preferences=502026.06—500——
Pref Trans.#Preferences=5002026.06—552——