Reinforcement Learning on Swimmer Velocity tasks suite (test)
36.32Average RewardTRPOADRC
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| TRPOADRCAlgorithm=TRPOADRC, Framework=TRPO, Controller=ADRC2026.01 | 36.32 | 19.03 | 12.16 | |
| CPPOPIDAlgorithm=CPPOPID, Framework=CPPO, Controller=PID2026.01 | 30.1 | 22.44 | 28.02 | |
| CPPOADRCAlgorithm=CPPOADRC, Framework=CPPO, Controller=ADRC2026.01 | 29.39 | 16.77 | 14.16 | |
| TRPOPIDAlgorithm=TRPOPID, Framework=TRPO, Controller=PID2026.01 | 28.72 | 21.34 | 37.85 |