Bus holding control on Simulated bidirectional bus corridor sigma_test = 1.5 1.0 (test)
-436.7Mean Episode RewardSAC
Evaluation Results
| Method | Links | |
|---|---|---|
| SACEmbedding=Full, sigma_train=2.02025.08 | -436.7 | |
| SACEmbedding=One-hot, sigma_train=1.02025.08 | -474.2 | |
| SACEmbedding=One-hot, sigma_train=1.52025.08 | -475.8 | |
| SACEmbedding=None, sigma_train=1.02025.08 | -478 | |
| SACEmbedding=Full, sigma_train=1.52025.08 | -479.4 | |
| SACEmbedding=None, sigma_train=1.52025.08 | -483.5 | |
| SACEmbedding=One-hot, sigma_train=2.02025.08 | -486 | |
| SACEmbedding=Full, sigma_train=1.02025.08 | -496.3 | |
| SACEmbedding=None, sigma_train=2.02025.08 | -517.2 | |
| TD3Embedding=Full, sigma_train=1.52025.08 | -634.7 | |
| DDPGEmbedding=One-hot, sigma_train=1.52025.08 | -952.5 | |
| TD3Embedding=One-hot, sigma_train=1.02025.08 | -959.6 | |
| TD3Embedding=One-hot, sigma_train=2.02025.08 | -979.8 | |
| TD3Embedding=One-hot, sigma_train=1.52025.08 | -979.9 | |
| DDPGEmbedding=Full, sigma_train=1.52025.08 | -981.5 | |
| TD3Embedding=None, sigma_train=2.02025.08 | -982.8 | |
| TD3Embedding=Full, sigma_train=2.02025.08 | -983 | |
| TD3Embedding=None, sigma_train=1.02025.08 | -989.5 | |
| DDPGEmbedding=Full, sigma_train=2.02025.08 | -989.9 | |
| DDPGEmbedding=None, sigma_train=2.02025.08 | -990.6 | |
| TD3Embedding=None, sigma_train=1.52025.08 | -991.9 | |
| DDPGEmbedding=Full, sigma_train=1.02025.08 | -992.2 | |
| DDPGEmbedding=One-hot, sigma_train=2.02025.08 | -992.6 | |
| TD3Embedding=Full, sigma_train=1.02025.08 | -994.4 | |
| DDPGEmbedding=One-hot, sigma_train=1.02025.08 | -995.2 | |
| DDPGEmbedding=None, sigma_train=1.02025.08 | -996.3 | |
| DDPGEmbedding=None, sigma_train=1.52025.08 | -1,003.2 |