1
$\begingroup$

As pictured here.

https://www.youtube.com/watch?v=kopoLzvh5jY

OpenAI implements a study for reinforcement learning with multiple learning agents which appear adversarial. "Millions of rounds" they say allowed these players to learn behaviors. The question is, are they really learning ? If once the algorithm they used was finished and the environment changed would the encoded data and decisions the algorithm learns apply and replicate what was 'learned' in any other virtual environment with the same overall rules ?

$\endgroup$

1 Answer 1

1
$\begingroup$

You can use the code available here, especially now that Mujoco simulator is free, and you can try it for yourself! From what I have seen, agents learn some of these behaviors described in the paper but lots of the time they behave chaotic. I do not think the agents perform well or solve the problem. Mainly, the study focuses on the emergence of some interesting behaviors and not on performance based on some score.

The agents were trained in random versions of the hide&seek environment so they are able to generalize within the same environment. They do not use pixels as inputs and instead they use coordinates, locations, velocities etc. This means that if you design your own environment with mujoco-world generator and have almost everything the same except the environment configuration you could possibly test how well the model generalizes.

$\endgroup$
1
  • $\begingroup$ I would kind of expect them to use other things since thats how my turret ai worked when i invested the time to recreate the semi working version that occasionally skipped the target and went full circle to reach the target :P $\endgroup$
    – John Sohn
    Oct 28, 2021 at 1:13

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.