Universal Policies to Learn Them All

Abstract

We explore a collaborative and cooperative multi-agent reinforcement learning setting where a team of reinforcement learning agents attempt to solve a single cooperative task in a multi-scenario setting. We propose a novel multi-agent reinforcement learning algorithm inspired by universal value function approximators that not only generalizes over state space but also over a set of different scenarios. Additionally, to prove our claim, we are introducing a challenging 2D multi-agent urban security environment where the learning agents are trying to protect a person from nearby bystanders in a variety of scenarios. Our study shows that state-of-the-art multi-agent reinforcement learning algorithms fail to generalize a single task over multiple scenarios while our proposed solution works equally well as scenario-dependent policies.

arXiv commentarXiv admin note: substantial text overlap with arXiv:1809.04500

References in corpus (6)

• Continuous control with deep reinforcement learning
• Novel type of phase transition in a system of self-driven particles
• Human-level performance in first-person multiplayer games with population-based deep reinforcement learning
• Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability
• Emergent Coordination Through Competition
• Designing a Multi-Objective Reward Function for Creating Teams of Robotic Bodyguards Using Deep Reinforcement Learning