Offline Reinforcement Learning on halfcheetah medium-expert v2
108.1Normalized ScoreReBRAC
Evaluation Results
| Method | Links | |
|---|---|---|
| ReBRACCategory=Non-diffusion, Delay=No delay2026.03 | 108.1 | |
| SAIDCategory=Diffusion Planners, Delay=02026.03 | 106.2 | |
| DQLCategory=Diffusion Policies, Delay=No delay2026.03 | 96.8 | |
| DQL*Category=Diffusion Policies, Delay=No delay2026.03 | 95.9 | |
| DVCategory=Diffusion Planners, Delay=No delay2026.03 | 92.7 | |
| DiffuserCategory=Diffusion Planners, Delay=No delay2026.03 | 88.9 | |
| RLDPSetting=low-coverage2026.03 | 86.03 | |
| HILPSetting=low-coverage2026.03 | 68.47 | |
| CQLCategory=Non-diffusion, Delay=No delay2026.03 | 62.4 | |
| FBSetting=low-coverage2026.03 | 52.17 | |
| PSMSetting=low-coverage2026.03 | 49.92 | |
| BCCategory=Non-diffusion, Delay=No delay2026.03 | 35.8 | |
| SAIDCategory=Diffusion Planners, Delay=42026.03 | 32.8 | |
| SAIDCategory=Diffusion Planners, Delay=82026.03 | 4.5 | |
| DQL+SACategory=Baseline w/ delay, Delay=42026.03 | 2.9 | |
| DQL+SACategory=Baseline w/ delay, Delay=82026.03 | 2.1 | |
| SAIDCategory=Diffusion Planners, Delay=162026.03 | 1.9 | |
| DQL+SACategory=Baseline w/ delay, Delay=162026.03 | 1.4 |