Offline Reinforcement Learning (Robot Manipulation) on D4RL Manipulation v1
117Normalized ScoreValue Flows
Evaluation Results
| Method | Links | |
|---|---|---|
| Value FlowsPolicy Architecture=Flow Policies, Task=pen-expert-v12025.10 | 117 | |
| BCPolicy Architecture=Gaussian Policies, Task=pen-expert-v12025.10 | 110 | |
| BCPolicy Architecture=Gaussian Policies, Task=door-expert-v12025.10 | 105 | |
| Value FlowsPolicy Architecture=Flow Policies, Task=door-expert-v12025.10 | 104 | |
| BCPolicy Architecture=Gaussian Policies, Task=pen-human-v12025.10 | 71 | |
| Value FlowsPolicy Architecture=Flow Policies, Task=pen-human-v12025.10 | 67 |