d3rlpy.metrics.comparer.compare_continuous_action_diff¶
-
d3rlpy.metrics.comparer.
compare_continuous_action_diff
(base_algo, window_size=1024)[source]¶ Returns scorer function of action difference between algorithms.
This metrics suggests how different the two algorithms are in continuous action-space. If the algorithm to compare with is near-optimal, the small action difference would be better.
\[\mathbb{E}_{s_t \sim D} [(\pi_{\phi_1}(s_t) - \pi_{\phi_2}(s_t))^2]\]from d3rlpy.algos import CQL from d3rlpy.metrics.comparer import compare_continuous_action_diff cql1 = CQL() cql2 = CQL() scorer = compare_continuous_action_diff(cql1) squared_action_diff = scorer(cql2, ...)
Parameters: - base_algo (d3rlpy.algos.base.AlgoBase) – algorithm to comapre with.
- window_size (int) – mini-batch size to compute.
Returns: scorer function.
Return type: callable