def true_values_for_sample(self, states, actions, assume_optimal_policy: bool): string_actions = [] for action in actions: string_actions.append(self.features_to_action(action)) return GridworldBase.true_values_for_sample( self, states, string_actions, assume_optimal_policy )
def true_values_for_sample(self, states, actions, assume_optimal_policy: bool): string_actions = [] for action in actions: string_actions.append(self.features_to_action(action)) return GridworldBase.true_values_for_sample( self, states, string_actions, assume_optimal_policy )
def true_values_for_sample(self, states, actions, assume_optimal_policy: bool): string_actions = [] for action in actions: string_actions.append(self.ACTIONS[int(list(action.keys())[0]) - self.num_states]) return GridworldBase.true_values_for_sample(self, states, string_actions, assume_optimal_policy)