List your company

Reinforcement Learning on Gymnasium HalfCheetah

2,737ReturnCAPO
1,201.961,600.481,9992,397.52Mar 13, 2026

Evaluation results

MethodLinks
CAPOBackbone=(64, 64) MLP, Training steps=1M, Seeds=8, Compute-matched=true2026.032,737
CAPO-AvgBackbone=(64, 64) MLP, Training steps=1M, Seeds=8, Compute-matched=true2026.031,967
Best-of-KBackbone=(64, 64) MLP, Training steps=1M, Seeds=8, Compute-matched=true2026.031,940
TRPOBackbone=(64, 64) MLP, Training steps=1M, Seeds=8, Compute-matched=false2026.031,629
PPOBackbone=(64, 64) MLP, Training steps=1M, Seeds=8, Compute-matched=false2026.031,604
PPO-K×Backbone=(64, 64) MLP, Training steps=1M, Seeds=8, Compute-matched=true2026.031,532
PPO-SWABackbone=(64, 64) MLP, Training steps=1M, Seeds=8, Compute-matched=false2026.031,261