List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on hopper medium-replay

113Normalized ScoreProposed
-2.12827.76157.6587.539Jun 16, 2021Apr 13, 2022Feb 8, 2023Dec 6, 2023Oct 2, 2024Jul 30, 2025May 27, 2026
Updated 5mo ago

Evaluation results

MethodLinks
ProposedSeeds=52023.10113
Anti-exploration Method2026.02103.1
ATACSeeds=52023.10102.5
Q-ALIGN DT2026.05102.2
QT2026.05102
DMG2026.02101.9
SAC-RND2026.02100.5
QCS2026.05100.4
O-DICE2026.0299.9
GPC-SAC2026.0297.5
RADT2026.0595.7
DM2026.0595.4
IQLSeeds=52023.1094.7
IQL2026.0294.7
DC2026.0594.2
Exp. WeightAlgorithmic Template=One-step2021.0694.1
LSDT2026.0593.9
CGDT2026.0593.4
IQL2026.0592.1
COMBOSeeds=52023.1089.5
I-TAPNoise=1.252026.0284.43
L-MAPNoise=1.252026.0283.99
DT2026.0582.7
Easy BCQAlgorithmic Template=One-step2021.0677.3
I-TAPNoise=3.752026.0275.22
Rev. KL Reg.Algorithmic Template=One-step2021.0671
L-MAPNoise=3.752026.0270.06
DTReward Specification=Step-wise2024.0263.7
TD3+BC2026.0560.9
I-TAPNoise=7.52026.0256.96
QDTReward Specification=Step-wise2024.0252.1
DTReward Specification=Final Return2024.0250.8
L-MAPNoise=7.52026.0250.79
CQLReward Specification=Step-wise2024.0248.6
Fu et al.Algorithmic Template=Iterative2021.0648.6
TD3-CVAE2026.0246.7
TD3+BCSeeds=52023.1044.4
DTNoise=1.252026.0239.22
QDTReward Specification=Final Return2024.0238.7
OptiDICESeeds=52023.1036.4
CQL2026.0235.9
BEARSeeds=52023.1033.7
BCQSeeds=52023.1033.1
DTNoise=3.752026.0233.03
CQLSeeds=52023.1032.6
DTNoise=7.52026.0230.17
BCAlgorithmic Template=One-step2021.0621.2
CQLReward Specification=Final Return2024.027.7
DVDF-IGDF2025.127.4
DVDF-OTDF2025.125.6
OTDF2025.124.6
IGDF2025.124.1
BOSA2025.123.7
DARA2025.123.5
IQL2025.122.3