Bus holding control on Simulated bidirectional bus corridor sigma_test = 2.0 1.0 (test)
-554,200Mean Episode RewardSAC
Evaluation Results
| Method | Links | |
|---|---|---|
| SACEmbedding=Full, sigma_train=2.02025.08 | -554,200 | |
| SACEmbedding=One-hot, sigma_train=1.02025.08 | -585,700 | |
| SACEmbedding=One-hot, sigma_train=1.52025.08 | -594,000 | |
| SACEmbedding=None, sigma_train=1.02025.08 | -602,500 | |
| SACEmbedding=Full, sigma_train=1.52025.08 | -608,400 | |
| SACEmbedding=None, sigma_train=1.52025.08 | -611,300 | |
| SACEmbedding=One-hot, sigma_train=2.02025.08 | -617,200 | |
| SACEmbedding=Full, sigma_train=1.02025.08 | -622,700 | |
| SACEmbedding=None, sigma_train=2.02025.08 | -651,600 | |
| TD3Embedding=Full, sigma_train=1.52025.08 | -780,200 | |
| TD3Embedding=None, sigma_train=2.02025.08 | -1,219,300 | |
| TD3Embedding=None, sigma_train=1.52025.08 | -1,226,100 | |
| DDPGEmbedding=One-hot, sigma_train=2.02025.08 | -1,227,300 | |
| TD3Embedding=None, sigma_train=1.02025.08 | -1,227,500 | |
| DDPGEmbedding=One-hot, sigma_train=1.52025.08 | -1,239,600 | |
| TD3Embedding=One-hot, sigma_train=1.02025.08 | -1,243,100 | |
| DDPGEmbedding=None, sigma_train=2.02025.08 | -1,243,900 | |
| TD3Embedding=Full, sigma_train=1.02025.08 | -1,245,400 | |
| TD3Embedding=One-hot, sigma_train=1.52025.08 | -1,247,600 | |
| DDPGEmbedding=Full, sigma_train=1.02025.08 | -1,251,400 | |
| DDPGEmbedding=None, sigma_train=1.02025.08 | -1,253,100 | |
| TD3Embedding=One-hot, sigma_train=2.02025.08 | -1,253,500 | |
| DDPGEmbedding=Full, sigma_train=1.52025.08 | -1,255,400 | |
| DDPGEmbedding=Full, sigma_train=2.02025.08 | -1,257,900 | |
| DDPGEmbedding=One-hot, sigma_train=1.02025.08 | -1,259,600 | |
| DDPGEmbedding=None, sigma_train=1.52025.08 | -1,260,000 | |
| TD3Embedding=Full, sigma_train=2.02025.08 | -1,268,200 |