# Potential Based Reshaping: Any Potential Function?

The paper states that every potential function won't alter the optimal policy. I lack of understanding why is that.

The definition:

$$R' = R + F$$ with $$F = \gamma\Phi(s') - \Phi(s)$$

where $$\gamma$$ may be $$0.9$$

If I have the following setup:

• on the left is my $$R$$.
• on the right my potential function $$\Phi(s)$$
• the top left is the start state, the top right is the goal state The reward for the red route is: $$(0 + 0.9 * 100 - 0) + (1 + 0.9 * 0 - 100) = -9$$.

And the reward for the blue route is: $$(-1 + 0) + (1 + 0) = 0$$.

So, for me, it seems like the blue route is better than the optimal red route and thus the optimal policy changed. Do I have erroneous thoughts here?

• Which paper are you talking about? – nbro Feb 16 at 1:53

The same $$\gamma = 0.9$$ that you use in the definition $$F \doteq \gamma \Phi(s') - \Phi(s)$$ should also be used as the discount factor in computing returns for multi-step trajectories. So, rather than simply adding up all the rewards for your different time-steps for the different trajectories, you should discount them by $$\gamma$$ for every time step that expires.
$$0 + (0.9 \times -1) + (0.9^2 \times 0) + (0.9^3 \times 1) = -0.9 + 0.729 = -0.171,$$
$$(0 + 0.9 \times 100 - 0) + 0.9 \times (1 + 0.9 \times 0 - 100) = 90 - 89.1 = 0.9.$$