Reinforcement Learning on MuJoCo w/o humanoid v4
423.4Runtime (seconds)PDA
Evaluation Results
| Method | Links | |
|---|---|---|
| PDAHardware=Intel i7-14700K, Environment steps=1M, Number of parallel runs=52026.03 | 423.4 | |
| TRPOHardware=Intel i7-14700K, Environment steps=1M, Number of parallel runs=52026.03 | 512.3 | |
| NPGHardware=Intel i7-14700K, Environment steps=1M, Number of parallel runs=52026.03 | 566.5 | |
| PPOHardware=Intel i7-14700K, Environment steps=1M, Number of parallel runs=52026.03 | 677.8 |