Loading
Feedback

dipam_chakraborty 0

Name

Dipam Chakraborty

Location

IN

Badges

0
0
1

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

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

Latest submissions

See All
graded 94599
graded 94551
graded 93732

3D seismic image Interpretation by Machine Learning

Latest submissions

No submissions made in this challenge.
Gold 0
Silver 0
Bronze 1
Trustable
May 16, 2020

Badges


  • May 16, 2020

  • May 16, 2020

  • May 16, 2020

  • May 16, 2020

  • May 16, 2020

  • May 16, 2020

  • May 16, 2020
  • Has filled their profile page
    May 16, 2020

  • May 16, 2020

  • May 16, 2020
Participant Rating
priteshgohil 0
Participant Rating
  • Gamma NeurIPS 2020: Procgen Competition
    View

IIT-M RL-ASSIGNMENT-2-GRIDWORLD

Welcome to your 2nd Assignment!

Yesterday

Hi @jaswanthi_mandalapu

It looks like the error says you need to accept the challenge rules. Can you please accept the rules then try submitting again.

Multi-Agent Behavior: Representation, Model

Can we use training data from task 1 or 2 for task 3?

9 days ago

Hi @sungbinchoi

Yes, you can use training data of Task 1 for 2 and 3. Feel free to use all the data at your disposal.

You can even use some unsupervised learning on the test sequences.

What is the shape of a frame stands for?

18 days ago

Hi @Lin_Yan_Liang

The each mouse’s keypoint coordinate is a 2D (X,y) coordinate.

2 Mice
2 Coordinates
7 keypoints

Does the clear your doubt?

RL-Taxi

RL notebook

About 1 month ago

Hi nischith_shadagopan,

Its not important for submission.

RLIITM-1

Rewards for out of grid states

About 1 month ago

Hi,

No, out of grid states do not have to be considered.

Can you please provide a link where it is?

RL-VI

Any questions about the assignment? Ask them here!

About 1 month ago

I think your TAs must have communicated that its supposed to be individual states and not matrix norm.

If you think about it matrix norm isn’t even a valid way, two arrays [0,0,1] and [1,0,0] would have the same norm.

Any questions about the assignment? Ask them here!

About 1 month ago

Hi mizhaan_prajiy_maniy,

Its a effect of how numpy arrays are printed vs how the image is shown in the diagram. Please rotate/transpose as needed for your visualization.

Best Regards,
Dipam

NeurIPS 2020: Procgen Competition

How to find subtle implementation details

4 months ago

Hi @lars12llt

Our full code is in Pytorch. However, I wrote entirely custom code on Pytorch for this competition as I was completely unfamiliar with rllib and wanted fine grained control over the entire code. My implementation works by basically subclassing TorchPolicy in rllib and writing the full training code in the learn_on_batch function. This admittedly removes rllib’s distributed learning benefits but allowed me to get comparable speed and score with Pytorch. Sorry I haven’t released the code yet, will be doing that soon.

Is it a preknowledge that we should select one of existing submissions for the final evaluation?

5 months ago

Hi @the_raven_chaser

I’m just curious as to why you think none of your submissions was prepared for the final evaluation? … Full disclosure we did not try to tune our submissions to the rest of the 10 environments either (Though we knew that the final evaluation will be done on 20 envs)

Questions about the competition timeline

6 months ago

Hello @jyotish

Thanks for the clarification, however this raises further questions. I think sample efficiency and generalization is a trade-off towards the end of training, which means with one submission we can be high scoring on sample efficiency but poor on generalization. Or we can improve generalization but reduce sample efficiency.

So the scenarios are:

There two tracks, two env configs while training, and two separate scoring metrics.

or

There is one track, one env config while training, one joint scoring metric.

Please clarify, which of the above is the case?

If there are two tracks (and two env configs while training), the selected submission can be used be near the top of sample efficiency but low generalization, or be in the middle of both leaderboards. Else, if there is a joint metric, we’d like to test that locally. We’ll plan our submissions accordingly.

Questions about the competition timeline

6 months ago

Hello @jyotish … Will there be a generalization track? If yes, can we select which submissions to use for generalization?

Can we change the x-axis on the Graphana viewer?

6 months ago

Hi @shivam, ok thanks for the info. Can it aslo be changed into values apart from clock time, for example environment steps?

Can we change the x-axis on the Graphana viewer?

6 months ago

Would be helpful for some analysis.

Anyone else getting MaxRuntimeExceeded in training?

6 months ago

I too recieved it again on #87296 in gemjourney and hovercraft.

Spot instances issues

7 months ago

Hi @xiaocheng_tang, I worked around it by saving the replay buffer as part of the checkpoint (with compression), but it seems like this is causing some new error MaxRuntimeExceeeded.

Waiting for organizers for a proper fix.

Anyone else getting MaxRuntimeExceeded in training?

7 months ago

Hi @jyotish I too recieved this error in #86264. I’d like to clarify that I’ve setup some code that saves the experience replay buffer along with the checkpoints because the reset of spot instances is messing up the replay buffer and really hurts performance. But the checkpoint saving and loading time doesn’t seem to be counted in ray “Time elapsed”. If this is the issue please suggest some proper solution to get replay buffers properly working with spot instances.

Spot instances issues

7 months ago

Hi @jyotish

Any suggestions on how to save the replay buffer properly with ray?

Anyone else having trouble with Plunder rollout timeout?

7 months ago

In my testing actually, there is high variance of result at 1000 runs but reduces at 5000 … and I still think rollouts can be much faster with more optimized code for parallel envs.

Seismic Facies Identification Challenge

📝 Explained by the Community | Win 4 x DJI Mavic Drones

6 months ago

EDA on facies variation by geographic axis

Here’s my EDA notebook on how the seismic data varies by geographic axis, along with some ideas for training.

A peek some of the stuff in the notebook

How the patterns look per label:

How the facies vary by z-axis


Splitting the data for training based on the EDA results

Do share your feedback. :blush: I’ll try to add training code soon.

The full colab notebook

Seismic-Facies-EDA - Colab

[Explainer] - EDA of Seismic data by geographic axis

6 months ago

EDA on variation by geographic axis

Here’s my EDA notebook on how the seismic data varies by geographic axis, along with some ideas for training.

A peek some of the stuff in the notebook

How the patterns look per label:

How the facies vary by z-axis


Splitting the data for training based on the EDA results

Do share your feedback. :blush:

Seismic-Facies-EDA - Colab

dipam_chakraborty has not provided any information yet.

Notebooks

Create Notebook