rr-learning/CausalWorld

reward wrong in reaching task

martius-lab opened this issue · 1 comments

In 'get_reward' in base_task you add the goal_distance to the reward. Given that you typically try to maximize the reward in the RL setting, shouldn't be the negative distance added to the reward?

Sorry for the late reply and thanks for pointing this out. Its actually the goal_reward instead which means 0 there is no overlap with the goal and 1 means full overlap with the goal (i.e succeeding in the task). We will change the naming accordingly.