List your company

Reinforcement Learning on Gymnasium HumanoidStandup

149,000Episodic ReturnCAPO
102,200114,350126,500138,650Mar 13, 2026

Evaluation results

MethodLinks
CAPOBackbone=(64, 64) MLP, Training steps=1M, Seeds=8, Compute-matched=true2026.03149,000
Best-of-KBackbone=(64, 64) MLP, Training steps=1M, Seeds=8, Compute-matched=true2026.03145,000
PPOBackbone=(64, 64) MLP, Training steps=1M, Seeds=8, Compute-matched=false2026.03143,000
CAPO-AvgBackbone=(64, 64) MLP, Training steps=1M, Seeds=8, Compute-matched=true2026.03141,000
TRPOBackbone=(64, 64) MLP, Training steps=1M, Seeds=8, Compute-matched=false2026.03134,000
PPO-SWABackbone=(64, 64) MLP, Training steps=1M, Seeds=8, Compute-matched=false2026.03121,000
PPO-K×Backbone=(64, 64) MLP, Training steps=1M, Seeds=8, Compute-matched=true2026.03104,000