d3rlpy.metrics.InitialStateValueEstimationEvaluator¶
- class d3rlpy.metrics.InitialStateValueEstimationEvaluator(*args, **kwds)[source]¶
Returns mean estimated action-values at the initial states.
This metrics suggests how much return the trained policy would get from the initial states by deploying the policy to the states. If the estimated value is large, the trained policy is expected to get higher returns.
\[\mathbb{E}_{s_0 \sim D} [Q(s_0, \pi(s_0))]\]References
- Parameters
episodes – Optional evaluation episodes. If it’s not given, dataset used in training will be used.
Methods
- __call__(algo, dataset)[source]¶
Computes metrics.
- Parameters
algo (d3rlpy.interface.QLearningAlgoProtocol) – Q-learning algorithm.
dataset (d3rlpy.dataset.replay_buffer.ReplayBuffer) – ReplayBuffer.
- Returns
Computed metrics.
- Return type