Reward scale

[Lucas Vazquez]

Some factors of reward scaling can generates instabilities, like described in #9 .

For alleviating this issue wouldn't it be a good idea to divide log_prob by reward_scale instead of multiplying the reward by it? Algorithmically speaking I think this would have the same effect.

[Tuomas Haarnoja]

That's right, you can alternatively divide log_prob by reward_scale for the same effect. It indeed can be slightly more stable especially in the beginning of learning.