Update reward to avoid stomping when no movement is required

[henri123lemoine]

We need to move away from "one policy per task" and towards "one policy for all tasks". One first step would be fixing the current problem where, when the walking policy is given 0s as its cmd, it still moves a lot, just without advancing (stomps without moving in any direction). One idea here would be to have the reward that encourages low dof lin vel be scaled up when the command is close enough to 0.

[jingxiangmo]

@budzianowski

[jingxiangmo]

yeah I think this is a really good idea.

[jingxiangmo]

there's a lot of refactoring to be done, @budzianowski do you know if Wesley is working on the min PPO implementation from scratch?