Bus holding control on Simulated bidirectional bus corridor sigma 1.0 (test)
-322.8Mean Episode RewardSAC
Evaluation Results
| Method | Links | |
|---|---|---|
| SACEmbedding=Full, sigma_train=2.02025.08 | -322.8 | |
| SACEmbedding=One-hot, sigma_train=1.52025.08 | -341.5 | |
| SACEmbedding=None, sigma_train=1.02025.08 | -343.5 | |
| SACEmbedding=Full, sigma_train=1.52025.08 | -347.4 | |
| SACEmbedding=None, sigma_train=1.52025.08 | -347.5 | |
| SACEmbedding=One-hot, sigma_train=2.02025.08 | -350.9 | |
| SACEmbedding=One-hot, sigma_train=1.02025.08 | -362.3 | |
| SACEmbedding=None, sigma_train=2.02025.08 | -366.2 | |
| SACEmbedding=Full, sigma_train=1.02025.08 | -369.1 | |
| TD3Embedding=Full, sigma_train=1.52025.08 | -492.1 | |
| TD3Embedding=None, sigma_train=1.52025.08 | -690.7 | |
| DDPGEmbedding=One-hot, sigma_train=2.02025.08 | -690.9 | |
| TD3Embedding=None, sigma_train=2.02025.08 | -694.2 | |
| TD3Embedding=None, sigma_train=1.02025.08 | -694.8 | |
| DDPGEmbedding=None, sigma_train=2.02025.08 | -698.3 | |
| DDPGEmbedding=One-hot, sigma_train=1.52025.08 | -698.6 | |
| DDPGEmbedding=Full, sigma_train=1.52025.08 | -698.7 | |
| DDPGEmbedding=None, sigma_train=1.02025.08 | -698.9 | |
| TD3Embedding=Full, sigma_train=2.02025.08 | -701.6 | |
| TD3Embedding=One-hot, sigma_train=1.52025.08 | -703.9 | |
| TD3Embedding=One-hot, sigma_train=1.02025.08 | -706.9 | |
| DDPGEmbedding=One-hot, sigma_train=1.02025.08 | -708.1 | |
| TD3Embedding=One-hot, sigma_train=2.02025.08 | -709.6 | |
| DDPGEmbedding=Full, sigma_train=2.02025.08 | -712.6 | |
| TD3Embedding=Full, sigma_train=1.02025.08 | -714 | |
| DDPGEmbedding=Full, sigma_train=1.02025.08 | -714.5 | |
| DDPGEmbedding=None, sigma_train=1.52025.08 | -721.2 |