Continuous Control on Gym MuJoCo
1.54Normalized Reward (TD3)MRS.Q
Evaluation Results
| Method | Links | |
|---|---|---|
| MRS.QMPC=true, Timesteps=1M2026.01 | 1.54 | |
| MR.QMPC=false, Timesteps=1M2026.01 | 1.46 | |
| SimbaV2MPC=false, Timesteps=1M2026.01 | 1.44 | |
| MR.Q + MPCMPC=true, Timesteps=1M2026.01 | 0.67 | |
| TD-M(PC)^2MPC=true, Timesteps=1M2026.01 | 0.62 | |
| BOOMMPC=true, Timesteps=1M2026.01 | 0.61 | |
| BMPCMPC=true, Timesteps=1M2026.01 | 0.54 | |
| TD-MPC2MPC=true, Timesteps=1M2026.01 | 0.38 |