updates
This commit is contained in:
@@ -71,10 +71,10 @@ class BallInACupReward(alr_reward_fct.AlrReward):
|
||||
dist_ctxt = self.dists_ctxt[-1]
|
||||
|
||||
# cost = self._get_stage_wise_cost(ball_in_cup, min_dist, dist_final, dist_ctxt)
|
||||
cost = 2 * (0.33 * min_dist + 0.33 * dist_final + 0.33 * dist_ctxt)
|
||||
cost = 2 * (0.5 * min_dist + 0.5 * dist_final + 0.1 * dist_ctxt)
|
||||
reward = np.exp(-1 * cost) - 1e-4 * action_cost
|
||||
stop_sim = True
|
||||
success = dist_final < 0.05 and ball_in_cup
|
||||
success = dist_final < 0.05 and dist_ctxt < 0.05
|
||||
else:
|
||||
reward = - 1e-4 * action_cost
|
||||
success = False
|
||||
|
||||
Reference in New Issue
Block a user