Learning to Share and Hide Intentions using Information Regularization
This addresses the challenge of multi-agent reinforcement learning in asymmetric information scenarios, but it is incremental as it builds on existing policy gradient methods with a novel regularization technique.
The paper tackled the problem of learning cooperative and competitive strategies in asymmetric information games without requiring models or interactions with other agents, by using an information-theoretic regularizer to control intention revelation, and demonstrated that this approach leads to more reward for a second agent in cooperative settings and less in competitive ones in two simple games.
Learning to cooperate with friends and compete with foes is a key component of multi-agent reinforcement learning. Typically to do so, one requires access to either a model of or interaction with the other agent(s). Here we show how to learn effective strategies for cooperation and competition in an asymmetric information game with no such model or interaction. Our approach is to encourage an agent to reveal or hide their intentions using an information-theoretic regularizer. We consider both the mutual information between goal and action given state, as well as the mutual information between goal and state. We show how to optimize these regularizers in a way that is easy to integrate with policy gradient reinforcement learning. Finally, we demonstrate that cooperative (competitive) policies learned with our approach lead to more (less) reward for a second agent in two simple asymmetric information games.