Continuous Control on DeepMind Control Suite Walker Walk
950.7RewardDreamer V3 with MLE regularisation
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Dreamer V3 with MLE regularisationMLE regularisation=true2024.10 | 950.7 | 0.1405 | |
| Dreamer V32024.10 | 948.6 | 0.1614 | |
| RC-TD3training steps=50 [k], seeds=3, w_target=0.52026.03 | 0.86 | — | |
| TD3training steps=50 [k], seeds=3, w_target=0.52026.03 | 0.85 | — | |
| RC-SACtraining steps=50 [k], seeds=3, w_target=0.52026.03 | 0.84 | — | |
| SACtraining steps=50 [k], seeds=3, w_target=0.52026.03 | 0.81 | — |