Door on Simulation
1Success RateViTaS
Evaluation results
| Method | Links | |
|---|---|---|
| ViTaSTask type=Reinforcement Learning (PPO), Training timesteps=3 × 10^6, Evaluation=Average of 5 random seeds2026.02 | 1 | |
| MVTTask type=Reinforcement Learning (PPO), Training timesteps=3 × 10^6, Evaluation=Average of 5 random seeds2026.02 | 1 | |
| CVTTask type=Reinforcement Learning (PPO), Training timesteps=3 × 10^6, Evaluation=Average of 5 random seeds2026.02 | 1 | |
| M3LTask type=Reinforcement Learning (PPO), Training timesteps=3 × 10^6, Evaluation=Average of 5 random seeds2026.02 | 1 | |
| ConcatTask type=Reinforcement Learning (PPO), Training timesteps=3 × 10^6, Evaluation=Average of 5 random seeds2026.02 | 1 | |
| VTTTask type=Reinforcement Learning (PPO), Training timesteps=3 × 10^6, Evaluation=Average of 5 random seeds2026.02 | 0.998 | |
| PoETask type=Reinforcement Learning (PPO), Training timesteps=3 × 10^6, Evaluation=Average of 5 random seeds2026.02 | 0.982 |