mlsanityData to 7 Oct 2026

Progressively Efficient Learning

arXiv 2310.13004 ↗First posted 13 Oct 2023cs.LG cs.AI cs.HCcited by 1

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

Assistant AI agents should be capable of rapidly acquiring novel skills and adapting to new user preferences. Traditional frameworks like imitation learning and reinforcement learning do not facilitate this capability because they support only low-level, inefficient forms of communication. In contrast, humans communicate with progressive efficiency by defining and sharing abstract intentions. Reproducing similar capability in AI agents, we develop a novel learning framework named Communication-Efficient Interactive Learning (CEIL). By equipping a learning agent with an abstract, dynamic language and an intrinsic motivation to learn with minimal communication effort, CEIL leads to emergence of a human-like pattern where the learner and the teacher communicate progressively efficiently by exchanging increasingly more abstract intentions. CEIL demonstrates impressive performance and communication efficiency on a 2D MineCraft domain featuring long-horizon decision-making tasks. Agents trained with CEIL quickly master new tasks, outperforming non-hierarchical and hierarchical imitation learning by up to 50% and 20% in absolute success rate, respectively, given the same number of interactions with the teacher. Especially, the framework performs robustly with teachers modeled after human pragmatic communication behavior.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 22 of its 40 references that are in the map. First posted on arXiv 13 Oct 2023.

Builds on

22 of 40 references.

Closest ancestors · 2

Same direction, newest first

  1. 2020Active Imitation Learning with Noisy Guidance26 May
  2. 2019A New Framework for Query Efficient Active Imitation Learning30 Dec

Other references · 20

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  5. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  6. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  7. 2020A Survey of Deep Active Learningcited by 547
  8. 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 350
  9. 2016Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivationcited by 282
  10. 2017Reverse Curriculum Generation for Reinforcement Learningcited by 185
  11. 2019Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learningcited by 100
  12. 2018Hierarchical Imitation and Reinforcement Learningcited by 88
8 more
  1. 2016Query-Efficient Imitation Learning for End-to-End Autonomous Drivingcited by 83
  2. 2017Learning how to Active Learn: A Deep Reinforcement Learning Approachcited by 79
  3. 2018Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Interventioncited by 77
  4. 2018Hierarchical Reinforcement Learning for Zero-shot Generalization with Subtask Dependenciescited by 43
  5. 2019Reinforcement Learning based Curriculum Optimization for Neural Machine Translationcited by 29
  6. 2021Interactive Learning from Activity Descriptioncited by 26
  7. 2020Reinforced Curriculum Learning on Pre-trained Neural Machine Translation Modelscited by 20
  8. 2021A Framework for Learning to Request Rich and Contextually Useful Information from Humanscited by 12

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Language-Guided World Models: A Model-Based Approach to AI Controlcited by 12

Similar, not cited

Close in wording, no citation either way

  1. 2026The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMs
  2. 2019Learning to Interactively Learn and Assist
  3. 2025In-Context Reinforcement Learning via Communicative World Models
  4. 2025Communicating Plans, Not Percepts: Scalable Multi-Agent Coordination with Embodied World Models
  5. 2019Learning to Request Guidance in Emergent Communication
  6. 2024Learning Translations: Emergent Communication Pretraining for Cooperative Language Acquisition
  7. 2020Imitating Interactive Intelligence
  8. 2025Training Language Models for Social Deduction with Multi-Agent Reinforcement Learning