AIcrowd | lukasz_kidzinski

0 Follower

0 Following

lukasz_kidzinski

Activity

Apr

May

Jun

Jul

Aug

Sep

Oct

Nov

Dec

Jan

Feb

Mar

Apr

Mon

Wed

Fri

Ratings Progression

Challenge Categories

Challenges Entered

Completed

NeurIPS 2019: Learn to Move - Walk Around

Stanford Neuromuscular Biomechanics Laboratory

Reinforcement Learning on Musculoskeletal Models

Latest submissions

See All

failed	16970	Sun, 29 Sep 2019 23:36:17
failed	16784	Thu, 26 Sep 2019 08:01:41
failed	16741	Wed, 25 Sep 2019 07:25:07

Participant	Rating

Participant	Rating

lukasz_kidzinski has not joined any teams yet...

NeurIPS 2019: Learn to Move - Walk Around

High memory usage - Memory leak?

Over 4 years ago

Hi, that’s unfortunately an issue that had been there for a while now

It might be solved in the new releases of OpenSim, so you might want to try install OpenSim from the source https://github.com/opensim-org/opensim-core

Reset simulator to specific state (e.g., state previously seen during an episode)

Over 4 years ago

Hi, you would need to loop through all variables of the state, serialize them and reinitialize the state. We don’t have a function for that yet, but it should be technically possible. Here is some useful starting point

Please follow up in that issue (or start another one in github) – it will be easier for me to bring in developers of OpenSim to the discussion.

Reset simulator to specific state (e.g., state previously seen during an episode)

Over 4 years ago

Hi! These two functions should do the job

github.com

stanfordnmbl/osim-rl/blob/master/osim/env/osim.py#L243-L250


def get_state(self):
    return opensim.State(self.state)


def set_state(self, state):
    self.state = state
    self.istep = int(self.state.getTime() / self.stepsize) # TODO: remove istep altogether
    self.reset_manager()

You can access the OpenSim model through

github.com

stanfordnmbl/osim-rl/blob/master/osim/env/osim.py#L269


# The amin purpose of this class is to provide wrap all 
# the functions of OpenAI gym. It is still an abstract
# class but closer to OpenSim. The actual classes of
# environments inherit from this one and:
# - select the model file
# - define the rewards and stopping conditions
# - define an obsernvation as a function of state
class OsimEnv(gym.Env):
    action_space = None
    observation_space = None
    osim_model = None
    istep = 0
    verbose = False


    visualize = False
    spec = None
    time_limit = 1e10


    prev_state_desc = None


    model_path = None # os.path.join(os.path.dirname(__file__), '../models/MODEL_NAME.osim')

I hope that helps!

Winning Solution of last year's competition

Almost 5 years ago

And here is the paper describing top solutions with links to github repos https://arxiv.org/abs/1902.02441

lukasz_kidzinski has not provided any information yet.

Notebooks

Create Notebook

Filters

Private

Notebooks

Create Notebook

Filters

Private

Location

Badges

Activity

Ratings Progression

Challenge Categories

Challenges Entered

NeurIPS 2019: Learn to Move - Walk Around

Latest submissions

NeurIPS 2019: Learn to Move - Walk Around

High memory usage - Memory leak?

Reset simulator to specific state (e.g., state previously seen during an episode)

Reset simulator to specific state (e.g., state previously seen during an episode)

Winning Solution of last year's competition

Notebooks

Notebooks