d3rlpy.metrics.scorer.td_error_scorer¶
-
d3rlpy.metrics.scorer.
td_error_scorer
(algo, episodes)[source]¶ Returns average TD error (in negative scale).
This metics suggests how Q functions overfit to training sets. If the TD error is large, the Q functions are overfitting.
\[\mathbb{E}_{s_t, a_t, r_{t+1}, s_{t+1} \sim D} [Q_\theta (s_t, a_t) - (r_t + \gamma \max_a Q_\theta (s_{t+1}, a))^2]\]- Parameters
algo (d3rlpy.metrics.scorer.AlgoProtocol) – algorithm.
episodes (List[d3rlpy.dataset.Episode]) – list of episodes.
- Returns
negative average TD error.
- Return type