d3rlpy.metrics.scorer.dynamics_observation_prediction_error_scorer¶
- d3rlpy.metrics.scorer.dynamics_observation_prediction_error_scorer(dynamics, episodes)[source]¶
Returns MSE of observation prediction (in negative scale).
This metrics suggests how dynamics model is generalized to test sets. If the MSE is large, the dynamics model are overfitting.
\[\mathbb{E}_{s_t, a_t, s_{t+1} \sim D} [(s_{t+1} - s')^2]\]where \(s' \sim T(s_t, a_t)\).
- Parameters
dynamics (d3rlpy.metrics.scorer.DynamicsProtocol) – dynamics model.
episodes (List[d3rlpy.dataset.Episode]) – list of episodes.
- Returns
negative mean squared error.
- Return type