erickvs
/

tqc-Hopper-v4-hand-edited

Reinforcement Learning

stable-baselines3

deep-reinforcement-learning

Eval Results (legacy)

Model card Files Files and versions

tqc-Hopper-v4-hand-edited / edit_program.json

Commit History

Nov 7 8 days ago

04:22
Hand-edited TQC hopper: one number stops it falling, no training (made with WSP Lab)

erickvs

Verified signature
1df5d72