dodox/fancy_gym
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

biac normal cost

Browse Source
This commit is contained in:
Maximilian Huettenrauch 2021-02-16 18:47:08 +01:00
parent 7eef78d620
commit 420fe10506
1 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
alr_envs/mujoco/ball_in_a_cup/ball_in_a_cup_reward.py
View File

@ -61,7 +61,7 @@ class BallInACupReward(alr_reward_fct.AlrReward):
success = False success = False
if self.check_collision(sim): if self.check_collision(sim):
reward = - 1e-5 * action_cost - 1000 reward = - 1e-4 * action_cost - 1000
stop_sim = True stop_sim = True
return reward, success, stop_sim return reward, success, stop_sim
@ -70,12 +70,13 @@ class BallInACupReward(alr_reward_fct.AlrReward):
dist_final = self.dists_final[-1] dist_final = self.dists_final[-1]
dist_ctxt = self.dists_ctxt[-1] dist_ctxt = self.dists_ctxt[-1]
cost = self._get_stage_wise_cost(ball_in_cup, min_dist, dist_final, dist_ctxt) # cost = self._get_stage_wise_cost(ball_in_cup, min_dist, dist_final, dist_ctxt)
reward = np.exp(-1 * cost) - 1e-5 * action_cost cost = 2 * (0.33 * min_dist + 0.33 * dist_final + 0.33 * dist_ctxt)
reward = np.exp(-1 * cost) - 1e-4 * action_cost
stop_sim = True stop_sim = True
success = dist_final < 0.05 and ball_in_cup success = dist_final < 0.05 and ball_in_cup
else: else:
reward = - 1e-5 * action_cost reward = - 1e-4 * action_cost
success = False success = False
return reward, success, stop_sim return reward, success, stop_sim