multiagent-particle-envs
multiagent-particle-envs copied to clipboard
openai
Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"
Hi, Can anyone explain why is the communication signal of size 10 in simple_reference. It is the output of actor NN along with physical action of size 5 but i...
Hi, i created some landmarks as obstacles in my scenario like simple_tag.py, but i found that the default observation function to entity_pos only record landmarks' center positions, without any info...
I am trying to make few landmarks as stationary lines and few as rectangular blocks. I could change render() function to get either everything as square or circle by editing...
Traceback (most recent call last): File "/home/shy/桌面/multiagent-particle-envs-master/bin/interactive.py", line 6, in from multiagent.environment import MultiAgentEnv File "/home/shy/桌面/multiagent-particle-envs-master/bin/../multiagent/environment.py", line 5, in from multiagent.multi_discrete import MultiDiscrete File "/home/shy/桌面/multiagent-particle-envs-master/bin/../multiagent/multi_discrete.py", line 7, in from gym.spaces...
Are those environments compatible with OpenAI baselines implementation? At first sights, it looks like the agents in `openai/baselines` don't support environments with an observable list. For example the code below...
when I use this code to interactively view moving to landmark scenario (see others in ./scenarios/): bin/interactive.py --scenario simple.py, the error is as follows: ` warnings.warn(colorize('%s: %s'%('WARN', msg % args),...
Could someone provide a scenario when landmark is movable?
Hi developer(s), Please check out this: https://github.com/openai/multiagent-particle-envs/blob/69ee7f85811c77ee651722bc3c332677b2195da1/multiagent/rendering.py#L232 line 232: ` for p in self.v: glVertex3f(p[0], p[1],0) # draw each vertex ` line 237: ` for p in self.v: glVertex3f(p[0], p[1],0)...
I see the env.step() function returns the observation of all the agents. Is there any way to get global state information?
Traceback (most recent call last): File "C:/Users/gajam/multiagent-particle-envs/bin/interactive.py", line 36, in env.render() File "C:\Users\gajam\multiagent-particle-envs\bin\..\multiagent\environment.py", line 261, in render results.append(self.viewers[i].render(return_rgb_array = mode=='rgb_array')) File "C:\Users\gajam\multiagent-particle-envs\bin\..\multiagent\rendering.py", line 110, in render self.window.flip() File "C:\Users\gajam\Anaconda3\lib\site-packages\pyglet\window\win32\__init__.py", line...
