Reinforcement Learning on InvManagementLostSalesEnv v0
472.3Avg Episodic RewardPDA
Evaluation results
| Method | Links | |
|---|---|---|
| PDAEnvironment steps=1M, Number of seeds=10, Tests per epoch=102026.03 | 472.3 | |
| PPOEnvironment steps=1M, Number of seeds=10, Tests per epoch=102026.03 | 447.4 | |
| TRPOEnvironment steps=1M, Number of seeds=10, Tests per epoch=102026.03 | 432.3 | |
| NPGEnvironment steps=1M, Number of seeds=10, Tests per epoch=102026.03 | 431.5 |