There has been a resurgence of interest in multiagent reinforcement learning (MARL), due partly to the recent success of deep neural networks. The simplest form of MARL is independent reinforcement learning (InRL), where each agent treats all of its experience as part of its (non stationary) environment. In this paper, we first observe that policies learned using InRL can overfit to the other agents' policies during training, failing to sufficiently generalize during execution. We introduce a new metric, joint-policy correlation, to quantify this effect. We describe a meta-algorithm for general MARL, based on approximate best responses to mixtures of policies generated using deep reinforcement learning, and empirical game theoretic analysis to compute meta-strategies for policy selection.

Machine Learning critically relies on the assumption that the training data is representative of the unseen instances a learner faces at test time.

The second step is reward modeling, which is the origin of the name "reward-based".

As a central example, we highlight the case one agent is no-swap and the other's regret is

Neural Information Processing Systems http://nips.cc/

In standard reinforcement learning (RL), a learning agent seeks to optimize the overall reward. However, many key aspects of a desired behavior are more naturally expressed as constraints.

Neural Information Processing Systems http://nips.cc/