When Policies Read Each Other: Teaching Agents to Cooperate by Reading the Code
Opening — Why this matters now Multi-agent systems are finally leaving the toy world. Autonomous traders negotiate with other bots. Supply-chain agents coordinate across firms. AI copilots increasingly share environments with other AI copilots. And yet, most multi-agent reinforcement learning (MARL) systems are still stuck with a primitive handicap: agents cannot meaningfully understand what other agents are doing. ...