PandaReachDense
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Goal-conditioned Reinforcement Learning | Modified PandaReachDense Joint space, +N+G v3 | Average Reward-7.63 | 4 | |
| Goal-conditioned Reinforcement Learning | Modified PandaReachDense Joint space, -N+G v3 | Average Reward-7.64 | 4 | |
| Goal-conditioned Reinforcement Learning | PandaReachDense Modified Joint space, +N-G v3 | Avg Reward-5.03 | 4 | |
| Goal-conditioned Reinforcement Learning | PandaReachDense Modified End-effector space, +N+G v3 | Average Reward-4.11 | 4 | |
| Goal-conditioned Reinforcement Learning | Modified PandaReachDense End-effector space, -N+G v3 | Average Reward-3.36 | 4 | |
| Goal-conditioned Reinforcement Learning | Modified PandaReachDense End-effector space, +N-G v3 | Avg Reward-2.25 | 4 |
Showing 6 of 6 rows