Minor issues in GA experiment

[adityauser]

Issue 1:
At line:

deep-neuroevolution/es_distributed/ga.py

Line 230 in 6ab22e1

eval_rews, eval_length = policy.rollout(env) # eval rollouts don't obey task_data.timestep_limit

The rollout function returns 3 objects, due to which we getting an error:
ValueError: too many values to unpack (expected 2)
It could be solved by replacing line 230 with:
eval_rews, eval_length, _ = policy.rollout(env)
Issue 2:
At line:

deep-neuroevolution/es_distributed/ga.py

Line 143 in 6ab22e1

lengths_n2 = np.array([r.lengths_n2 for r in curr_task_results])

It should be lengths_n2 = np.concatenate([r.lengths_n2 for r in curr_task_results]) very much similar to

deep-neuroevolution/es_distributed/es.py

Line 276 in 6ab22e1

lengths_n2 = np.concatenate([r.lengths_n2 for r in curr_task_results])

Otherwise lengths_n2.mean() and lengths_n2.sum() will have multiple dimension.