Continuous Control on MuJoCo HalfCheetah v2 (train)
6,173Mean ReturnMCPO
Evaluation results
| Method | Links | |
|---|---|---|
| MCPOEnvironment steps=10M, Number of runs=52022.04 | 6,173 | |
| Mean ψEnvironment steps=10M, Number of runs=5, N=402022.04 | 4,942 | |
| MDPOEnvironment steps=10M, Number of runs=52022.04 | 4,774 | |
| PPOEnvironment steps=10M, Number of runs=52022.04 | 4,753 | |
| TRPOEnvironment steps=10M, Number of runs=52022.04 | 2,811 | |
| TRGPPOEnvironment steps=10M, Number of runs=52022.04 | 2,811 |