Mobile Catch on Simulation
64.9Success RateViTaS
Evaluation Results
| Method | Links | |
|---|---|---|
| ViTaSTask type=Reinforcement Learning (PPO), Training timesteps=3 × 10^6, Evaluation=Average of 5 random seeds2026.02 | 64.9 | |
| CVTTask type=Reinforcement Learning (PPO), Training timesteps=3 × 10^6, Evaluation=Average of 5 random seeds2026.02 | 64.2 | |
| VTTTask type=Reinforcement Learning (PPO), Training timesteps=3 × 10^6, Evaluation=Average of 5 random seeds2026.02 | 53.3 | |
| MVTTask type=Reinforcement Learning (PPO), Training timesteps=3 × 10^6, Evaluation=Average of 5 random seeds2026.02 | 44.2 | |
| M3LTask type=Reinforcement Learning (PPO), Training timesteps=3 × 10^6, Evaluation=Average of 5 random seeds2026.02 | 15.8 | |
| ConcatTask type=Reinforcement Learning (PPO), Training timesteps=3 × 10^6, Evaluation=Average of 5 random seeds2026.02 | 0.6 | |
| PoETask type=Reinforcement Learning (PPO), Training timesteps=3 × 10^6, Evaluation=Average of 5 random seeds2026.02 | 0.4 |