List your company

Offline Meta Reinforcement Learning on Ant-dir (out-of-distribution)

410.7Average ReturnSPC
146.644215.197283.75352.303Mar 3, 2026

Evaluation results

MethodLinks
SPCZero-shot=true2026.03410.7
UNICORN-SSZero-shot=true2026.03405.9
CSROZero-shot=true2026.03399.2
FOCALZero-shot=true2026.03368.8
UNICORN-SUPZero-shot=true2026.03211.4
DORAZero-shot=true2026.03156.8