Real-Time Physics Simulation Forum 2018-11-06T04:59:48+00:00 https://pybullet.org/Bullet/phpBB3/app.php/feed/topic/12460 2018-11-06T04:59:48+00:00 2018-11-06T04:59:48+00:00 https://pybullet.org/Bullet/phpBB3/viewtopic.php?p=41566#p41566 <![CDATA[Re: Reset gym environment with an observation]]> PyBullet Quickstart Guide.

Statistics: Posted by Erwin Coumans — Tue Nov 06, 2018 4:59 am

]]> 2018-10-16T15:10:28+00:00 2018-10-16T15:10:28+00:00 https://pybullet.org/Bullet/phpBB3/viewtopic.php?p=41517#p41517 <![CDATA[Reset gym environment with an observation]]>
I would like to create a controller for the gym Hopper environment. Therefore I would like to create a state/dynamics equation to use afterwards finite difference. This dynamic function should have an observation and action as input and the next state as output, so somewhat similar to this pseudo-code:

Code: 

def state_equation(observation, action):env.set_state(observation) #THIS function is missing..next_state, _, _, _ = env.step(action)return next_state
Therefore it is necessary to reset the environment with a given observation (and change the observations/state to calculate the derivative..). And this is the problem: I cannot find a solution to set the environment to a specific state given an observation.

I know that I can use following commands to save and restore a state but this doesn't help since I want to set the environment to a state given any observation without visiting and saving it before..

Code: 

 stateId = p.saveState()  p.restoreState(stateId)
So in the end my question is: Is there any way to realize the dynamics function ? Or a solution to reset the environment with a given observation? Or any other advice to solve my problem?

Thank you very much in advance for any advice and kind regards !

Statistics: Posted by i14d4 — Tue Oct 16, 2018 3:10 pm

]]>