multiagent-particle-envs

multiagent-particle-envs copied to clipboard

lucas-spangher

Discrete type while action value is not one-hot....

1

CatIIIIIIII

Creating the boundary of the environment

6

We are trying to add boundaries to the environment, but when we check the code of the entity in core.py, there is only the size property, from our understanding, we...

lyp741

Closing rendered environment

2

Is anyone else having trouble closing the environment after it has been rendered? After I run the following code, the window just hangs there. env.render() ** stuff env.close()

Khev

Questions about agent`s state information in MADDPG

1

Take the three predators and two escapers in simple_tag as an example. I tried to print the status information of these five agents and got an array. The status information...

zxm-NEU

when using env.render, it's hard to wait for the game playing 1,000,000 times and see the last game process. So, how to restore and even record those game processes?

aoi997

Hi everyone, I am implementing the PPO algorithm on this environment. I succesfully run a few experiments in the single agent simple environment which I used for debugging. Now I...

Kimonili

If want to change the scenario from simple to other, how should I do?

1

There should be command line in interactive.py , what is the key word? Thanks.

silkyrose

Could someone provide a scenario when landmark is movable?

3

Seems like all landmarks in scenarios are unmovable. Wondering if someone can provide a case when they are movable?

zddkjmuner

Hi! [Here](https://github.com/openai/multiagent-particle-envs/blob/69ee7f85811c77ee651722bc3c332677b2195da1/multiagent/scenarios/simple_speaker_listener.py#L61) you can find a small type, which you may change from "reward" to "world".

tessavdheiden