Description
Model-based policy optimization (MBPO) is a model-based, online, off-policy reinforcement learning algorithm. For more information on the different types of reinforcement learning agents
Technical Details
| Framework | MITRE D3FEND |
| Ontology URI | d3f:Model-basedPolicyOptimization |
| Local Identifier | Model-basedPolicyOptimization |
| Publication Status | Exists in ontology only |