# Robots Learn Increasingly Complex Tasks with Intrinsic Motivation and Automatic Curriculum Learning

arXiv: https://arxiv.org/abs/2202.10222 · HTML: https://mlsanity.com/paper/2202.10222/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 40 references that are in the map.
- First posted on arXiv 11 Feb 2022.

## Builds on (most cited first, 13 of 13)

- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection](https://mlsanity.com/paper/1603.02199/) (2016)
- [Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation](https://mlsanity.com/paper/1604.06057/) (2016)
- [Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning](https://mlsanity.com/paper/1708.02190/) (2017)
- [CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning](https://mlsanity.com/paper/1810.06284/) (2018)
- [Active Learning of Inverse Models with Intrinsically Motivated Goal Exploration in Robots](https://mlsanity.com/paper/1301.4862/) (2013)
- [GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms](https://mlsanity.com/paper/1802.05054/) (2018)
- [Action Representations in Robotics: A Taxonomy and Systematic Classification](https://mlsanity.com/paper/1809.04317/) (2018)
- [Hierarchical Affordance Discovery using Intrinsic Motivation](https://mlsanity.com/paper/2009.10968/) (2020)
- [Active choice of teachers, learning strategies and goals for a socially guided intrinsic motivation learner](https://mlsanity.com/paper/1804.06819/) (2018)
- [Socially Guided Intrinsic Motivation for Robot Learning of Motor Skills](https://mlsanity.com/paper/1804.07269/) (2018)
- [Learning a Set of Interrelated Tasks by Using Sequences of Motor Policies for a Strategic Intrinsically Motivated Learner](https://mlsanity.com/paper/1810.04877/) (2018)
- [Intrinsically Motivated Open-Ended Multi-Task Learning Using Transfer Learning to Discover Task Hierarchy](https://mlsanity.com/paper/2102.09854/) (2021)

## Built on by (most cited first, 3 of 3)

- [AURA: Autonomous Upskilling with Retrieval-Augmented Agents](https://mlsanity.com/paper/2506.02507/) (2025)
- [Goal Space Abstraction in Hierarchical Reinforcement Learning via Reachability Analysis](https://mlsanity.com/paper/2309.07168/) (2023)
- [tinyDSM: A Framework for Skill Modeling and Development for Resource-Constrained Millirobots](https://mlsanity.com/paper/2608.17596/) (2026)

## Abstract (arXiv)

Multi-task learning by robots poses the challenge of the domain knowledge: complexity of tasks, complexity of the actions required, relationship between tasks for transfer learning. We demonstrate that this domain knowledge can be learned to address the challenges in life-long learning. Specifically, the hierarchy between tasks of various complexities is key to infer a curriculum from simple to composite tasks. We propose a framework for robots to learn sequences of actions of unbounded complexity in order to achieve multiple control tasks of various complexity. Our hierarchical reinforcement learning framework, named SGIM-SAHT, offers a new direction of research, and tries to unify partial implementations on robot arms and mobile robots. We outline our contributions to enable robots to map multiple control tasks to sequences of actions: representations of task dependencies, an intrinsically motivated exploration to learn task hierarchies, and active imitation learning. While learning the hierarchy of tasks, it infers its curriculum by deciding which tasks to explore first, how to transfer knowledge, and when, how and whom to imitate.