Re:Emergent Tool Use from Multi-Agent Interaction
by tlb on Tuesday September 17, 2019 @02:40PM
(#20998670)
The animations are nice, compared to a default visualization with dots and lines moving around. Was this done just for the public release, or was it worth it to researchers to have an eye-pleasing visualization while doing the experiments?
[ Parent
| on HN ]
Re:Emergent Tool Use from Multi-Agent Interaction
by visarga on Tuesday September 17, 2019 @03:33PM
(#20999180)
The environment was actually an important part of the project. It does physics simulation. Having such a 'realistic' environment allowed the agents to discover all sorts of cheats (they appear at the end of the article).
Re:Emergent Tool Use from Multi-Agent Interaction
by boardwaalk on Tuesday September 17, 2019 @03:56PM
(#20999403)
They're talking about the visualization, not the physics. The agents aren't getting visual input. That would make things much, much slower.
Re:Emergent Tool Use from Multi-Agent Interaction
by vertoc on Tuesday September 17, 2019 @04:12PM
(#20999556)
Right but to fully understand what's going on you need to also visualize the physics in a 3D world - just dots and lines and squares wouldn't fully show what's going on. This may be close to the simplest visualization that made sense
Re:Emergent Tool Use from Multi-Agent Interaction
by PhasmaFelis on Tuesday September 17, 2019 @07:09PM
(#21000988)
An accurate 3D visualization could have been a lot simpler than this. The actors are most likely modeled physically as simple cylinders; all the character animations are extraneous. And there's plenty of subtle effects in the seekers' vision cones, the reflective floor, the uneven box landscape outside, etc.
So, as tlb said, I'm curious if all of that was added for the public release, or if the researchers set it up while running the experiments. It seems like it would be fun.
Re:Emergent Tool Use from Multi-Agent Interaction
by breck on Tuesday September 17, 2019 @06:28PM
(#21000737)
The visualizations look great, but wouldn't run on an N64, which had many physics games. I'm wondering the same thing as the OP--was this advanced level of graphics used during the research, or was the styling added after the fact for readers? A low res visualization seems like it would do the job equally well, but maybe not. Curious what they are finding and whether there are benefits to having a great looking visualization during the EDA phase.