Location
Badges
Activity
Ratings Progression
Challenge Categories
Participant | Rating |
---|
Participant | Rating |
---|
NeurIPS 2019: Learn to Move - Walk Around
How can i get the 97D body state in the evaluation environment?
Over 4 years agoor how can i convert the 14-key dict to the 4-key one?
How can i get the 97D body state in the evaluation environment?
Over 4 years agoIn 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 agoIn 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 2Γ11Γ11 2D target velocities on an 11Γ11 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 thestep
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.
How can i get the 97D body state in the evaluation environment?
Over 4 years agoThanks 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,