Pen Rotate on Simulation
99.2Success RateViTaS
Evaluation results
| Method | Links | |
|---|---|---|
| ViTaSTask type=Reinforcement Learning (PPO), Training timesteps=3 × 10^6, Evaluation=Average of 5 random seeds2026.02 | 99.2 | |
| CVTTask type=Reinforcement Learning (PPO), Training timesteps=3 × 10^6, Evaluation=Average of 5 random seeds2026.02 | 79.6 | |
| MVTTask type=Reinforcement Learning (PPO), Training timesteps=3 × 10^6, Evaluation=Average of 5 random seeds2026.02 | 77.1 | |
| M3LTask type=Reinforcement Learning (PPO), Training timesteps=3 × 10^6, Evaluation=Average of 5 random seeds2026.02 | 73.1 | |
| ConcatTask type=Reinforcement Learning (PPO), Training timesteps=3 × 10^6, Evaluation=Average of 5 random seeds2026.02 | 2.9 | |
| VTTTask type=Reinforcement Learning (PPO), Training timesteps=3 × 10^6, Evaluation=Average of 5 random seeds2026.02 | 0.7 | |
| PoETask type=Reinforcement Learning (PPO), Training timesteps=3 × 10^6, Evaluation=Average of 5 random seeds2026.02 | 0.3 |