Wrappers¶
ObjectSelectorWrapper¶
-
class
causal_world.wrappers.
ObjectSelectorWrapper
(env)[source]¶ -
-
reset
()[source]¶ Resets the environment to the current starting state of the environment.
- Returns
(nd.array) specifies the observations returned after resetting the environment. Again, it follows the observation_mode specified.
-
step
(action)[source]¶ Used to step through the enviroment.
- Parameters
action – (nd.array) specifies which action should be taken by the robot, should follow the same action mode specified.
- Returns
(nd.array) specifies the observations returned after stepping through the environment. Again, it follows the observation_mode specified.
-
MovingAverageActionEnvWrapper¶
-
class
causal_world.wrappers.
MovingAverageActionEnvWrapper
(env, widow_size=8, initial_value=0)[source]¶ -
__init__
(env, widow_size=8, initial_value=0)[source]¶ - Parameters
env – (causal_world.CausalWorld) the environment to convert.
widow_size – (int) the window size for avergaing and smoothing the actions.
initial_value – (float) intial values to fill the window with.
-
DeltaActionEnvWrapper¶
-
class
causal_world.wrappers.
DeltaActionEnvWrapper
(env)[source]¶ -
__init__
(env)[source]¶ A delta action wrapper for the environment to turn the actions to a delta wrt the previous action executed.
- Parameters
env – (causal_world.CausalWorld) the environment to convert.
-
CurriculumWrapper¶
-
class
causal_world.wrappers.
CurriculumWrapper
(env, intervention_actors, actives)[source]¶ -
__init__
(env, intervention_actors, actives)[source]¶ - Parameters
env – (causal_world.CausalWorld) the environment to convert.
intervention_actors – (list) list of intervention actors
actives – (list of tuples) each tuple indicates (episode_start, episode_end, episode_periodicity, time_step_for_intervention)
-
reset
()[source]¶ Resets the environment to the current starting state of the environment.
- Returns
(nd.array) specifies the observations returned after resetting the environment. Again, it follows the observation_mode specified.
-
step
(action)[source]¶ Used to step through the enviroment.
- Parameters
action – (nd.array) specifies which action should be taken by the robot, should follow the same action mode specified.
- Returns
(nd.array) specifies the observations returned after stepping through the environment. Again, it follows the observation_mode specified.
-
HERGoalEnvWrapper¶
-
class
causal_world.wrappers.
HERGoalEnvWrapper
(env, activate_sparse_reward=False)[source]¶ -
__init__
(env, activate_sparse_reward=False)[source]¶ - Parameters
env – (causal_world.CausalWorld) the environment to convert.
activate_sparse_reward – (bool) True to activate sparse rewards.
-
close
()[source]¶ closes the environment in a safe manner should be called at the end of the program.
- Returns
None
-
compute_reward
(achieved_goal, desired_goal, info)[source]¶ Used to calculate the reward given a hypothetical situation that could be used in hindsight experience replay algorithms variants. Can only be used in the spare reward setting for the other setting it can be tricky here.
- Parameters
achieved_goal – (nd.array) specifies the achieved goal as bounding boxes of objects by default.
desired_goal – (nd.array) specifies the desired goal as bounding boxes of goal shapes by default.
info – (dict) not used for now.
- Returns
(float) the final reward achieved given the hypothetical situation.
-
render
(mode='human', **kwargs)[source]¶ Returns an RGB image taken from above the platform.
- Parameters
mode – (str) not taken in account now.
- Returns
(nd.array) an RGB image taken from above the platform.
-
reset
()[source]¶ Resets the environment to the current starting state of the environment.
- Returns
(nd.array) specifies the observations returned after resetting the environment. Again, it follows the observation_mode specified.
-
seed
(seed=None)[source]¶ Used to set the seed of the environment, to reproduce the same randomness.
- Parameters
seed – (int) specifies the seed number
- Returns
(int in list) the numpy seed that you can use further.
-
property
spec
¶ return:
-
step
(action)[source]¶ Used to step through the enviroment.
- Parameters
action – (nd.array) specifies which action should be taken by the robot, should follow the same action mode specified.
- Returns
(nd.array) specifies the observations returned after stepping through the environment. Again, it follows the observation_mode specified.
-
property
unwrapped
¶ return:
-
ProtocolWrapper¶
-
class
causal_world.wrappers.
ProtocolWrapper
(env, protocol)[source]¶ -
__init__
(env, protocol)[source]¶ - Parameters
env – (causal_world.CausalWorld) the environment to convert.
protocol – (causal_world.evaluation.ProtocolBase) protocol to evaluate.
-
reset
()[source]¶ Resets the environment to the current starting state of the environment.
- Returns
(nd.array) specifies the observations returned after resetting the environment. Again, it follows the observation_mode specified.
-
step
(action)[source]¶ Used to step through the enviroment.
- Parameters
action – (nd.array) specifies which action should be taken by the robot, should follow the same action mode specified.
- Returns
(nd.array) specifies the observations returned after stepping through the environment. Again, it follows the observation_mode specified.
-