Learning Hierarchical Teaching Policies for Cooperative Agents

Abstract

Collective learning can be greatly enhanced when agents effectively exchange knowledge with their peers. In particular, recent work studying agents that learn to teach other teammates has demonstrated that action advising accelerates team-wide learning. However, the prior work has simplified the learning of advising policies by using simple function approximations and only considered advising with primitive (low-level) actions, limiting the scalability of learning and teaching to complex domains. This paper introduces a novel learning-to-teach framework, called hierarchical multiagent teaching (HMAT), that improves scalability to complex environments by using the deep representation for student policies and by advising with more expressive extended action sequences over multiple levels of temporal abstraction. Our empirical evaluations demonstrate that HMAT improves team-wide learning progress in large, complex domains where previous approaches fail. HMAT also learns teaching policies that can effectively transfer knowledge to different teammates with knowledge of different tasks, even when the teammates have heterogeneous action spaces.

arXiv commentPresented at AAMAS 2020; arXiv version added with the appendix

References in corpus (12)

• Continuous control with deep reinforcement learning
• Categorical Reparameterization with Gumbel-Softmax
• Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
• Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation
• FeUdal Networks for Hierarchical Reinforcement Learning
• Data-Efficient Hierarchical Reinforcement Learning
• Reinforcement and Imitation Learning via Interactive No-Regret Learning
• Coordinated Multi-Agent Imitation Learning
• Learning to Teach
• Probabilistic Recursive Reasoning for Multi-Agent Reinforcement Learning
• Learning Abstract Options
• Learning to Explore with Meta-Policy Gradient