OneDTransitionRewardModel w/ SACAgent Agent playing mbrl-Hopper-v2
This is a trained model of a OneDTransitionRewardModel w/ SACAgent agent playing mbrl-Hopper-v2 using MBRL-Lib.
Usage (with MBRL-Lib)
TODO: Add your code
from mbrl import ...
...
- Downloads last month
- 1
Evaluation results
- mean_reward on mbrl-Hopper-v2self-reported87.70 +/- 1.10