428516056abe41f135133e732a8d44af6ce9a234,rllib/utils/exploration/random.py,Random,get_torch_exploration_action,#Random#Any#Any#,83

Before Change

        return action, logp

    def get_torch_exploration_action(self, action_dist, explore):
        tensor_fn = torch.LongTensor if \
            type(self.action_space) in [Discrete, MultiDiscrete] else \
            torch.FloatTensor
        if explore:
            // Unsqueeze will be unnecessary, once we support batch/time-aware
            // Spaces.
            a = self.action_space.sample()

After Change

                action_dist.required_model_output_shape(
                    self.action_space, self.model.model_config))
            // Add a batch dimension.
            if len(action_dist.inputs.shape) == len(req) + 1:
                a = np.expand_dims(a, 0)
            action = torch.from_numpy(a).to(self.device)
        else:
            action = action_dist.deterministic_sample()
        logp = torch.zeros(

Instances