![](https://images.aicrowd.com/images/participants/image_file/29226/7513203.png)
Location
Badges
Activity
Ratings Progression
Challenge Categories
Challenges Entered
Revolutionising Interior Design with AI
Latest submissions
Behavioral Representation Learning from Animal Poses.
Latest submissions
See Allgraded | 177565 | ||
graded | 177560 | ||
graded | 177538 |
ASCII-rendered single-player dungeon crawl game
Latest submissions
Latest submissions
Participant | Rating |
---|
Participant | Rating |
---|
MABe 2022: Mouse Triplets
NeurIPS 2021 - The NetHack Challenge
![](https://images.aicrowd.com/100x100/images/participants/image_file/29226/7513203.png)
Identify environment across steps while learning
About 3 years agoMy idea was to make something like an βassisted AIβ. Instead of waiting millions of steps to avoid climbing the entrance stairs, eating kobold corpses and walking into walls, I would like to make an actor able to choose between not-obviously-stupid actions .
So for this I would like to have a state attached to the actor or the environment ( where I would store things like βthe stairdown is there even if there is a bow dropped on itβ, the intrinsics etc ), and alter the βcall to inferenceβ . Obviously this prevents the model to learn about some actions ( for example when asked to say y/n at: βBeware, there will be no returnβ, I force Direction.SE when the actor happily samples randomly on the action space ), but I am not sure there is a value, in this case, to let it try something else.
So while training and testing I want to be able to βhelp choose sensible optionsβ.
Note that while training, overriding the βstep()β function of the environment does not do what I want because I want to learn the forced action, not the original one.
I understand I should use a gym wrapper around the environment, this seems to be an allowed method, I have to see if this way I will be able to add one more key to the observations ( for example an uuid computed at reset() time ).
![](https://images.aicrowd.com/100x100/images/participants/image_file/29226/7513203.png)
Access to screen_descriptions observation key
About 3 years agoThe screen_descriptions observation key is not accessible in the NethackChallenge class and itβs not possible to enable it for submissions ( or is it ?? ). Also the HELP ( β?β ) function is disabled even if itβs available in the game and itβs the only way to know if the dog is tame and if a monster is peaceful.
Is it possible to enable the key for the challenge ?
![](https://images.aicrowd.com/100x100/images/participants/image_file/29226/7513203.png)
Identify environment across steps while learning
About 3 years agoWith the torchbeast system, I understand I have access , at each step, to the environment and the actor state in the inference function while learning , but the batch size is dynamic and I have found no identifier which would allow me to know which environment/actor are in the batch.
It seems all the batch.get_inputs() is managed by the torchbeast library, I would rather not recompile it.
Does anyone have a smart hack ?
How does ranking work?
Over 2 years agoHello, I do not understand how the ranking works in this challenge.
The last submission I made had a F1 score of 0.153 and it has been βgraded with a score of 0.0β.
I was also βcongratulated for my first submissionβ, but actually it was the sixth .
Should I select the submission for the ranking? Or is there a bug? Or is the F1 score irrelevant for ranking?