Loading
0 Follower
0 Following
Mizhaan

Location

US

Badges

3
1
1

Activity

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

Ratings Progression

Loading...

Challenge Categories

Loading...

Challenges Entered

IIT-M, Reinforcement Learning, Value Iteration

Latest submissions

See All
graded 126128
graded 126047
submitted 126035

Reinforcement Learning, IIT-M, assignment 1

Latest submissions

See All
graded 126680
graded 126656
failed 126651

Latest submissions

See All
graded 132291
graded 132094
graded 132092

Latest submissions

See All
graded 143163
graded 143162
graded 143160

Latest submissions

See All
graded 158652
graded 158651
graded 158650

Train your RL agents

Latest submissions

No submissions made in this challenge.
Participant Rating
Participant Rating
Mizhaan has not joined any teams yet...

IITM RL Final Project-b5d2e6

Submission limit

Over 2 years ago

Another reason why the submission should be increased (maybe to 10-20) is because of errors while submitting, as inference failed errors still count as a submission.

Mismatch in limits of observation space for CARTPOLE and MOUNTAINCAR

Over 2 years ago

Hi, when using the command “env.observation_space.high” and “env.observation_space.low” for the above-mentioned two environments, it shows + \infty and - \infty respectively for all elements.

Does this mean that we just hardcode the limits (from the given table) for the two environments or will this issue be corrected, please do let us know!

In addition, when sampling the next state through env.step(), the value for theta_dot exceeds 5.

IIT-M RL-ASSIGNMENT-2-TAXI

Unable to submit post 20th april

Over 2 years ago

Hi, it looks like a lot of us are unable to perform a submission post 20th. It says “Error in notifying rails about the uploaded file”. Please look into it as the deadline has been pushed to 24th.

RL-Taxi

Any questions about this assignment? Ask them here!

Over 2 years ago

Yes I understand, however I was trying to narrow down the problem as to where the ‘inference failed’ error was popping up. It pops up when I call the function dp_solve with a modified class object.

Any questions about this assignment? Ask them here!

Over 2 years ago

Hi, so there is an issue regarding inference failed. If i call the function dp_solve(env2) on another variation of the env object (such as chaning the policy), this is resulting in an inference failed error. Please look into this s it can be fixed, also if possible, please increase the number of submissions for the day cause most of my submissions went to waste for debugging.

RL-VI

Reducing tolerance for value grid, please resubmit your code

Over 2 years ago

im having the same issue, please let us know what is the scoring criteria

Any questions about the assignment? Ask them here!

Over 2 years ago

Ok will make sure, also when you earlier said that the tolerance was 1e-8, did you mean the matrix norm ( || J_{i+1} - J_i|| ) or the max abs ( \max_{s \in S} |J_{i+1}(s) - J_i(s)| )? Thank you!

Any questions about the assignment? Ask them here!

Over 2 years ago

Hi, the env params loaded in the notebook dont seem to correlate to the grid world 1 figure. The co-ordinates in the notebook are transposed, for instance, env.brown_out = (9,7) (i.e. 10th row, 8th column visually) and should be instead (7,9) to match figure 1.

However this doesnt affect the code, it may be an issue in Task 5 where we need to compare and contrast these 2 grid worlds. Please clarify this discrepancy, thank you!

Mizhaan has not provided any information yet.

Notebooks

Create Notebook