Loading
0 Follower
0 Following
quang_tran

Location

US

Badges

2
1
1

Activity

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

Ratings Progression

Loading...

Challenge Categories

Loading...

Challenges Entered

Measure sample efficiency and generalization in reinforcement learning using procedurally generated environments

Latest submissions

See All
graded 88531
graded 87203
failed 87170
Participant Rating
Participant Rating
  • Gamma NeurIPS 2020: Procgen Competition
    View

NeurIPS 2020: Procgen Competition

Choosing the best submission for the final evaluation

Over 3 years ago

When do we get to pick the submission for the final evaluation on all environments for 2 tracks?

Questions about the competition timeline

Over 3 years ago

Hey @jyotish, does the submission we pick have to be something we submitted previously, or it can be a new submission after round 2 ends? It doesn’t really make sense to pick something we previously submitted because those are for sample efficiency only.

Increase limit on SageMaker training instances

Over 3 years ago

Thanks @jyotish. I just made additional requests for spot instances.

Increase limit on SageMaker training instances

Over 3 years ago

By default the number of ml.p3.2xlarge instances one can use for training is 0. And one wants to use more to train on 16 env parallelly, one needs to contact supports for an increase in limit. I contacted support and they said that it will take a while. Since this problem will apply to everyone, is there any way the organizer can make the process of increasing limit faster?

Number of environments in round 2

Over 3 years ago

Thank you for the information

Number of environments in round 2

Over 3 years ago

Agree, came across many sample efficient algorithms that require more than 2 hours to run 8M steps

Number of environments in round 2

Over 3 years ago

Currently, I see that round 2 has only 6 procgen games instead of 16. Is that temporary or will that be until the end of round 2?

Forming team with another competitor in round 2

Over 3 years ago

Thank you very much!

Forming team with another competitor in round 2

Over 3 years ago

Is it possible for me to collaborate with another competitor and form a team in round 2?

High average reward but low score

Over 3 years ago


I’m a little bit confused. My mean reward is 8.134, yet my mean normalized reward is 0. I have 3 questions:

  • What are R_min and R_max used to calculate the normalized score for coinrun?
  • How many episodes are used to calculate the evaluation scores?
  • How are these evaluation episodes (levels) different from the episodes given in training?

Number of levels in round 1?

Over 3 years ago

What’s the number of levels allowed for training in round 1? Are the evaluation levels same as training level for round 1? If they are not the same, how are they different?

What are the evaluation environments?

Over 3 years ago

What are the evaluation environments for round 1?

quang_tran has not provided any information yet.