mlsanityData to 7 Oct 2026

Explainable Action Advising for Multi-Agent Reinforcement Learning

arXiv 2211.07882 ↗First posted 15 Nov 2022cs.AI cs.LG cs.MAcited by 10

Not on the map. Why?

Abstract (arXiv)

Action advising is a knowledge transfer technique for reinforcement learning based on the teacher-student paradigm. An expert teacher provides advice to a student during training in order to improve the student's sample efficiency and policy performance. Such advice is commonly given in the form of state-action pairs. However, it makes it difficult for the student to reason with and apply to novel states. We introduce Explainable Action Advising, in which the teacher provides action advice as well as associated explanations indicating why the action was chosen. This allows the student to self-reflect on what it has learned, enabling advice generalization and leading to improved sample efficiency and learning performance - even in environments where the teacher is sub-optimal. We empirically show that our framework is effective in both single-agent and multi-agent scenarios, yielding improved policy returns and convergence rates when compared to state-of-the-art methods

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 14 of its 35 references that are in the map. First posted on arXiv 15 Nov 2022.

Builds on

14 of 35 references.

References · 14

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2016Generative Adversarial Imitation Learningcited by 1,576
  3. 2017Counterfactual Multi-Agent Policy Gradientscited by 733
  4. 2018Explaining Explanations: An Overview of Interpretability of Machine Learningcited by 508
  5. 2018Verifiable Reinforcement Learning via Policy Extractioncited by 176
  6. 2018Reinforcement Learning from Imperfect Demonstrationscited by 74
  7. 2018Learning to Teach in Cooperative Multiagent Reinforcement Learningcited by 45
  8. 2019Teaching on a Budget in Multi-Agent Deep Reinforcement Learningcited by 14
  9. 2021HAMMER: Multi-Level Coordination of Reinforcement Learning Agents via Learned Messagingcited by 12
  10. 2020An Efficient Transfer Learning Framework for Multiagent Reinforcement Learningcited by 11
  11. 2017Learning to Teach Reinforcement Learning Agentscited by 10
  12. 2019Policy Distillation and Value Matching in Multiagent Reinforcement Learningcited by 10
2 more
  1. 2021Action Advising with Advice Imitation in Deep Reinforcement Learningcited by 10
  2. 2021Multi-Agent Advisor Q-Learningcited by 4

Built on by

Cited by year

Citing papers per year: 2023: 6; 2024: 1; 2025: 3.

10 papers.

  1. 2023Concept Learning for Interpretable Multi-Agent Reinforcement Learningcited by 18
  2. 2023Sample-Efficient Learning of Novel Visual Conceptscited by 8
  3. 2024Explaining Decisions of Agents in Mixed-Motive Gamescited by 4
  4. 2025Model-Agnostic Policy Explanations with Large Language Modelscited by 4
  5. 2023Explaining Agent Behavior with Large Language Modelscited by 3
  6. 2023Understanding Your Agent: Leveraging Large Language Models for Behavior Explanationcited by 3
  7. 2023Introspective Action Advising for Interpretable Transfer Learningcited by 2
  8. 2025Energy-Based Transfer for Reinforcement Learningcited by 1
  9. 2025Human-Allied Relational Reinforcement Learningcited by 1
  10. 2023Fidelity-Induced Interpretable Policy Extraction for Reinforcement Learningcited by 0