fixed seeding and tests

alr_envs/envs/mujoco/__init__.py

@@ -1,9 +1,9 @@
 from .beerpong.beerpong import BeerPongEnv, BeerPongEnvFixedReleaseStep, BeerPongEnvStepBasedEpisodicReward
 from .ant_jump.ant_jump import AntJumpEnv
-from .half_cheetah_jump.half_cheetah_jump import ALRHalfCheetahJumpEnv
+from .half_cheetah_jump.half_cheetah_jump import HalfCheetahJumpEnv
 from .hopper_jump.hopper_jump_on_box import HopperJumpOnBoxEnv
-from .hopper_throw.hopper_throw import ALRHopperThrowEnv
-from .hopper_throw.hopper_throw_in_basket import ALRHopperThrowInBasketEnv
+from .hopper_throw.hopper_throw import HopperThrowEnv
+from .hopper_throw.hopper_throw_in_basket import HopperThrowInBasketEnv
 from .reacher.reacher import ReacherEnv
-from .walker_2d_jump.walker_2d_jump import ALRWalker2dJumpEnv
+from .walker_2d_jump.walker_2d_jump import Walker2dJumpEnv
 from .hopper_jump.hopper_jump import HopperJumpEnv

alr_envs/envs/mujoco/beerpong/deprecated/beerpong.py

@@ -155,7 +155,7 @@ class BeerPongEnvStepBasedEpisodicReward(BeerPongEnv):
         return ob, reward, done, infos
 
 
-# class ALRBeerBongEnvStepBased(ALRBeerBongEnv):
+# class BeerBongEnvStepBased(ALRBeerBongEnv):
 #     def __init__(self, frame_skip=1, apply_gravity_comp=True, noisy=False, rndm_goal=False, cup_goal_pos=None):
 #         super().__init__(frame_skip, apply_gravity_comp, noisy, rndm_goal, cup_goal_pos)
 #         self.release_step = 62  # empirically evaluated for frame_skip=2!

alr_envs/envs/mujoco/half_cheetah_jump/half_cheetah_jump.py

@@ -8,7 +8,7 @@ import numpy as np
 MAX_EPISODE_STEPS_HALFCHEETAHJUMP = 100
 
 
-class ALRHalfCheetahJumpEnv(HalfCheetahEnv):
+class HalfCheetahJumpEnv(HalfCheetahEnv):
     """
     ctrl_cost_weight 0.1 -> 0.0
     """

alr_envs/envs/mujoco/hopper_throw/hopper_throw.py

@@ -7,7 +7,7 @@ import numpy as np
 MAX_EPISODE_STEPS_HOPPERTHROW = 250
 
 
-class ALRHopperThrowEnv(HopperEnv):
+class HopperThrowEnv(HopperEnv):
     """
     Initialization changes to normal Hopper:
     - healthy_reward: 1.0 -> 0.0 -> 0.1
@@ -98,7 +98,7 @@ class ALRHopperThrowEnv(HopperEnv):
 
 if __name__ == '__main__':
     render_mode = "human"  # "human" or "partial" or "final"
-    env = ALRHopperThrowEnv()
+    env = HopperThrowEnv()
     obs = env.reset()
 
     for i in range(2000):

alr_envs/envs/mujoco/hopper_throw/hopper_throw_in_basket.py

@@ -8,7 +8,7 @@ import numpy as np
 MAX_EPISODE_STEPS_HOPPERTHROWINBASKET = 250
 
 
-class ALRHopperThrowInBasketEnv(HopperEnv):
+class HopperThrowInBasketEnv(HopperEnv):
     """
     Initialization changes to normal Hopper:
     - healthy_reward: 1.0 -> 0.0
@@ -130,7 +130,7 @@ class ALRHopperThrowInBasketEnv(HopperEnv):
 
 if __name__ == '__main__':
     render_mode = "human"  # "human" or "partial" or "final"
-    env = ALRHopperThrowInBasketEnv()
+    env = HopperThrowInBasketEnv()
     obs = env.reset()
 
     for i in range(2000):

alr_envs/envs/mujoco/walker_2d_jump/walker_2d_jump.py

@@ -12,7 +12,7 @@ MAX_EPISODE_STEPS_WALKERJUMP = 300
 #  as possible, while landing at a specific target position
 
 
-class ALRWalker2dJumpEnv(Walker2dEnv):
+class Walker2dJumpEnv(Walker2dEnv):
     """
     healthy reward 1.0 -> 0.005 -> 0.0025 not from alex
     penalty 10 -> 0 not from alex
@@ -95,7 +95,7 @@ class ALRWalker2dJumpEnv(Walker2dEnv):
 
 if __name__ == '__main__':
     render_mode = "human"  # "human" or "partial" or "final"
-    env = ALRWalker2dJumpEnv()
+    env = Walker2dJumpEnv()
     obs = env.reset()
 
     for i in range(6000):