Laser Learning Environment: Insights on the challenges of coordination-critical multi-agent tasks

Yannick Molinghen, Raphaël Avalos, Mark Van Achter, Ann Nowe, Tom Lenaerts

Keywords: multi-agent, reinforcement learning, cooperative, environment

TL;DR: The Laser Learning Environment, a cooperative environment for MARL highlights the difficulty of escaping state space bottlenecks caused by interdependence and zero-incentive dynamics, necessitating novel methods for effective coordination.

Abstract: We introduce the Laser Learning Environment (LLE), a collaborative multi-agent reinforcement learning environment in which coordination is central. In LLE, agents depend on each other to make progress (interdependence), must jointly take specific sequences of actions to succeed (perfect coordination), and accomplishing those joint actions does not yield any intermediate reward (zero-incentive dynamics). The challenge of such problems lies in the difficulty of escaping state space bottlenecks caused by interdependence steps since escaping those bottlenecks is not rewarded. We test multiple state-of-the-art value-based MARL algorithms against LLE and show that they consistently fail at the collaborative task because of their inability to escape state space bottlenecks, even though they successfully achieve perfect coordination. We show that Q-learning extensions such as prioritised experience replay and n-steps return hinder exploration in environments with zero-incentive dynamics, and find that intrinsic curiosity with random network distillation is not sufficient to escape those bottlenecks. We demonstrate the need for novel methods to solve this problem and the relevance of LLE as cooperative MARL benchmark.