ML Day 2014 - Learning to Act in Multiagent Sequential Environments
1,803 views · Published 21 June 2016 · 31:06 · Indexed 8 November 2026
Channel: Microsoft Research · 2016 · Science & Technology
From routing to online auctions, many decision-making tasks for learning agents are carried out in the presence of other decision makers. I will give a brief overview of results developed in the context of adapting reinforcement-learning algorithms to work effectively in multiagent environments. Of particular interest is the idea that even simple scenarios, such as the well-known Prisoner’s dilemma, require agents to work together, bearing some individual risk, to arrive at mutually beneficial outcomes
