Loading
0 Follower
0 Following
gupengju

Location

CN

Badges

0
0
0

Activity

Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Apr
Mon
Wed
Fri

Ratings Progression

Loading...

Challenge Categories

Loading...

Challenges Entered

Latest submissions

See All
failed 8283
failed 8282
graded 8281

Latest submissions

See All
graded 17842
graded 10122
graded 10108
Participant Rating
Participant Rating
gupengju has not joined any teams yet...

NeurIPS 2019: Learn to Move - Walk Around

How can i get the 97D body state in the evaluation environment?

Over 4 years ago

Thanks a lot. The docker image aicrowd/neurips-learning-to-move-subcontractor:latest has updated and the local grader runs successfully now. And the new submit option is more convenient, :grinning:

How can i get the 97D body state in the evaluation environment?

Over 4 years ago

or how can i convert the 14-key dict to the 4-key one?:joy:

How can i get the 97D body state in the evaluation environment?

Over 4 years ago

In the following code,

observation = client.env_create()
while True:
    print(observation.keys())
    observation_np=obs2np(observation)
    observation_T=torch.from_numpy(observation_np).float().to(torch.device('cuda'))
    _action = model.target_policy(observation_T)
    [observation, reward, done, info] = client.env_step(_action.cpu())
    
    if done:
        observation = client.env_reset()
        if not observation:
            break
client.submit()

client.env_create() and client.env_reset() can get a dict of 4 keys
but the function client.env_step() still get a dict of 14 keys

How can i fixed this code.

thanks a lot.

How can i get the 97D body state in the evaluation environment?

Almost 5 years ago

In order to train a model locally and visualizably, using the following code we get an dict observation_2 that contains 4 keys and 339 numbers. These numbers contains an 2Γ—11Γ—11 2D target velocities on an 11Γ—11 grid and the 97D body state(242+97=339).

[observation_2, reward, done, info] = env.step(_action,obs_as_dict=True)

Here it says S is a 97D vector representing the body state.

But in the evaluation environment which is not visualizable, we can use the following code to get an dict observation containing 14 keys and 688 numbers,

[observation, reward, done, info] = client.env_step(_action)

And when I use the first code to get the observation_2, it reports the following error:

Attempt to call step function after max_steps=1000 in a single simulation. Please reset your environment before calling the step function after max_step s

and here is the question: how can i get the 97D body state in the evaluation environment?

thank you very much.

gupengju has not provided any information yet.