RunpeiDong
/

HERO

whole-body-control

end-effector-tracking

reinforcement-learning

Model card Files Files and versions

Commit History

model card: dataset archive URL + sha256

1afd7bc
verified

RunpeiDong commited on 1 day ago

model card

8bee47e
verified

RunpeiDong commited on 1 day ago

hero_export_v1 metadata sidecar

974f0b2
verified

RunpeiDong commited on 1 day ago

HERO example policy (dual-actor PPO export, delta anchor, Dex3)

79d467d
verified

RunpeiDong commited on 1 day ago

initial commit

1f34ff2
verified

RunpeiDong commited on 1 day ago