fix(exploration): typo self.ago -> self.algo in sample_func_logits

In MightyExplorationPolicy.sample_func_logits, the sac flag passed to
sample_nondeterministic_logprobs used self.ago instead of self.algo.
Because self.ago does not exist, this always resolved to False, meaning
the tanh-squash correction was never applied for SAC in this code path.

Author: jmtoepperwien

mighty/mighty_exploration/mighty_exploration_policy.py

@@ -111,7 +111,7 @@ def sample_func_logits(self, state_array):
         elif isinstance(out, tuple) and len(out) == 4:
             action = out[0]  # [batch, action_dim]
             log_prob = sample_nondeterministic_logprobs(
-                z=out[1], mean=out[2], log_std=out[3], sac=self.ago == "sac"
+                z=out[1], mean=out[2], log_std=out[3], sac=self.algo == "sac"
             )
             return action.detach().cpu().numpy(), log_prob