We present the first study on provably efficient randomized exploration in cooperative multi-agent reinforcement learning (MARL).

By incorporating the entropy term, we can ensure the diversity of the generated environments.

Reinforcement learning algorithms typically consider discrete-time dynamics, even though the underlying systems are often continuous in time.

The International Joint Conference on Artificial Intelligence (IJCAI) distinguished paper awards recognise some of the best papers presented at the conference each year. This year, during the conference opening ceremony, three articles were named as distinguished papers. Abstract: Normative Restraining Bolts (NRBs) adapt the restraining bolt technique (originally developed for safe reinforcement learning) to ensure compliance with social, legal, and ethical norms. While effective, NRBs rely on trial-and-error weight tuning, which hinders their ability to enforce hierarchical norms; moreover, norm updates require retraining. In this paper, we reformulate learning with NRBs as a multi-objective reinforcement learning (MORL) problem, where each norm is treated as a distinct objective.

We introduce inductive biases for positive signalling and positive listening, which ease this problem. In a simple one-step environment, we demonstrate how these biases ease the learning problem.

We thank the reviewers for their insightful comments and suggestions. We hope that the rebuttal will clarify the issues. There are two reasons why Algorithm 1 should be preferred in practice. RL algorithms (e.g., MBIE or Delayed-QL), Algorithm 2 is extremely conservative, leading to very slow convergence. Algorithm 1 can be seen as a "practical" version of Algorithm 2 We will clarify this point in the final version.

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

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

However, strikingly, this measure is independent of rewards and is a function of only the transitions.