Interestingly, in another game called Wolfpack (see gameplay video below), which requires close coordination to successfully cooperate, we find that greater capacity to implement complex strategies leads to more cooperation between agents, the opposite of the finding with Gathering. So, depending on the situation, having a greater capacity to implement complex strategies may yield either more or less cooperation. The new framework of sequential social dilemmas allows us to take into account not only the outcome of the interaction (as in the Prisoner’s dilemma), but also the difficulty of learning to implement a given strategy.
Source: https://deepmind.com/blog/article/understanding-agent-cooperation
More from Deep Mind - Latest Post
DeepMind AI Reduces Google Data Centre Cooling Bill by 40%
Source Node: 802629
Time Stamp: Jul 19, 2016
Safety-first AI for autonomous data centre cooling and industrial control
Source Node: 750995
Time Stamp: Aug 17, 2018
Advanced machine learning helps Play Store users discover personalised apps
Source Node: 748595
Time Stamp: Nov 18, 2019
AlphaFold: a solution to a 50-year-old grand challenge in biology
Source Node: 747253
Time Stamp: Nov 30, 2020