# Learning to Interactively Learn and Assist

arXiv: https://arxiv.org/abs/1906.10187 · HTML: https://mlsanity.com/paper/1906.10187/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jun 2019.

## Built on by (most cited first, 20 of 20)

- [Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization](https://mlsanity.com/paper/2103.04564/) (2021)
- [A Model-Based Solution to the Offline Multi-Agent Reinforcement Learning Coordination Problem](https://mlsanity.com/paper/2305.17198/) (2023)
- [Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Tasks](https://mlsanity.com/paper/2107.05825/) (2021)
- [Emergent Language: A Survey and Taxonomy](https://mlsanity.com/paper/2409.02645/) (2024)
- [Learning Vision-based Pursuit-Evasion Robot Policies](https://mlsanity.com/paper/2308.16185/) (2023)
- [AssistanceZero: Scalably Solving Assistance Games](https://mlsanity.com/paper/2504.07091/) (2025)
- [Learning Robust Real-Time Cultural Transmission without Human Data](https://mlsanity.com/paper/2203.00715/) (2022)
- [Combining Reward Information from Multiple Sources](https://mlsanity.com/paper/2103.12142/) (2021)
- [SocialAI: Benchmarking Socio-Cognitive Abilities in Deep Reinforcement Learning Agents](https://mlsanity.com/paper/2107.00956/) (2021)
- [Generative AI collective behavior needs an interactionist paradigm](https://mlsanity.com/paper/2601.10567/) (2026)
- [Learning Latent Representations to Co-Adapt to Humans](https://mlsanity.com/paper/2212.09586/) (2022)
- [Online Decision Mediation](https://mlsanity.com/paper/2310.18601/) (2023)
- [Observation Interference in Partially Observable Assistance Games](https://mlsanity.com/paper/2412.17797/) (2024)
- [Learning to Guide and to Be Guided in the Architect-Builder Problem](https://mlsanity.com/paper/2112.07342/) (2021)
- [The Oversight Game: Learning to Cooperatively Balance an AI Agent's Safety and Autonomy](https://mlsanity.com/paper/2510.26752/) (2025)
- [Temporal Induced Self-Play for Stochastic Bayesian Games](https://mlsanity.com/paper/2108.09444/) (2021)
- [SocialAI 0.1: Towards a Benchmark to Stimulate Research on Socio-Cognitive Abilities in Deep Reinforcement Learning Agents](https://mlsanity.com/paper/2104.13207/) (2021)
- [STAND: Self-Aware Precondition Induction for Interactive Task Learning](https://mlsanity.com/paper/2409.07653/) (2024)
- [Mixed-Initiative Dialog for Human-Robot Collaborative Manipulation](https://mlsanity.com/paper/2508.05535/) (2025)
- [Reinforcement Learning Problem Solving with Large Language Models](https://mlsanity.com/paper/2404.18638/) (2024)

## Abstract (arXiv)

When deploying autonomous agents in the real world, we need effective ways of communicating objectives to them. Traditional skill learning has revolved around reinforcement and imitation learning, each with rigid constraints on the format of information exchanged between the human and the agent. While scalar rewards carry little information, demonstrations require significant effort to provide and may carry more information than is necessary. Furthermore, rewards and demonstrations are often defined and collected before training begins, when the human is most uncertain about what information would help the agent. In contrast, when humans communicate objectives with each other, they make use of a large vocabulary of informative behaviors, including non-verbal communication, and often communicate throughout learning, responding to observed behavior. In this way, humans communicate intent with minimal effort. In this paper, we propose such interactive learning as an alternative to reward or demonstration-driven learning. To accomplish this, we introduce a multi-agent training framework that enables an agent to learn from another agent who knows the current task. Through a series of experiments, we demonstrate the emergence of a variety of interactive learning behaviors, including information-sharing, information-seeking, and question-answering. Most importantly, we find that our approach produces an agent that is capable of learning interactively from a human user, without a set of explicit demonstrations or a reward function, and achieving significantly better performance cooperatively with a human than a human performing the task alone.