# Active Task Randomization: Learning Robust Skills via Unsupervised Generation of Diverse and Feasible Tasks

arXiv: https://arxiv.org/abs/2211.06134 · HTML: https://mlsanity.com/paper/2211.06134/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 57 of its 79 references that are in the map.
- First posted on arXiv 11 Nov 2022.

## Builds on (most cited first, 30 of 57)

- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [Solving Rubik's Cube with a Robot Hand](https://mlsanity.com/paper/1910.07113/) (2019)
- [RLBench: The Robot Learning Benchmark & Learning Environment](https://mlsanity.com/paper/1909.12271/) (2019)
- [Sim-to-Real Transfer of Robotic Control with Dynamics Randomization](https://mlsanity.com/paper/1710.06537/) (2017)
- [Learning Quadrupedal Locomotion over Challenging Terrain](https://mlsanity.com/paper/2010.11251/) (2020)
- [Leveraging Procedural Generation to Benchmark Reinforcement Learning](https://mlsanity.com/paper/1912.01588/) (2019)
- [A simple neural network module for relational reasoning](https://mlsanity.com/paper/1706.01427/) (2017)
- [Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection](https://mlsanity.com/paper/1603.02199/) (2016)
- [Integrated Task and Motion Planning](https://mlsanity.com/paper/2010.01083/) (2020)
- [Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design](https://mlsanity.com/paper/2012.02096/) (2020)
- [RoboNet: Large-Scale Multi-Robot Learning](https://mlsanity.com/paper/1910.11215/) (2019)
- [Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics](https://mlsanity.com/paper/1703.09312/) (2017)
- [Automatic Goal Generation for Reinforcement Learning Agents](https://mlsanity.com/paper/1705.06366/) (2017)
- [Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets](https://mlsanity.com/paper/2109.13396/) (2021)
- [MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale](https://mlsanity.com/paper/2104.08212/) (2021)
- [Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hours](https://mlsanity.com/paper/1509.06825/) (2015)
- [RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitation](https://mlsanity.com/paper/1811.02790/) (2018)
- [ATISS: Autoregressive Transformers for Indoor Scene Synthesis](https://mlsanity.com/paper/2110.03675/) (2021)
- [Prioritized Level Replay](https://mlsanity.com/paper/2010.03934/) (2020)
- [Behavior From the Void: Unsupervised Active Pre-Training](https://mlsanity.com/paper/2103.04551/) (2021)
- [Evolving Curricula with Regret-Based Environment Design](https://mlsanity.com/paper/2203.01302/) (2022)
- [Active Domain Randomization](https://mlsanity.com/paper/1904.04762/) (2019)
- [Learning to Poke by Poking: Experiential Learning of Intuitive Physics](https://mlsanity.com/paper/1606.07419/) (2016)
- [PDDLStream: Integrating Symbolic Planners and Blackbox Samplers via Optimistic Adaptive Planning](https://mlsanity.com/paper/1802.08705/) (2018)
- [Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play](https://mlsanity.com/paper/1703.05407/) (2017)
- [Procedural Content Generation via Machine Learning (PCGML)](https://mlsanity.com/paper/1702.00539/) (2017)
- [DriveGAN: Towards a Controllable High-Quality Neural Simulation](https://mlsanity.com/paper/2104.15060/) (2021)
- [Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments](https://mlsanity.com/paper/1910.07224/) (2019)

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

- [Practice Makes Perfect: Planning to Learn Skill Parameter Policies](https://mlsanity.com/paper/2402.15025/) (2024)
- [Blox-Net: Generative Design-for-Robot-Assembly Using VLM Supervision, Physics Simulation, and a Robot with Reset](https://mlsanity.com/paper/2409.17126/) (2024)
- [Generate, Transfer, Adapt: Learning Functional Dexterous Grasping from a Single Human Demonstration](https://mlsanity.com/paper/2601.05243/) (2026)

## Abstract (arXiv)

Solving real-world manipulation tasks requires robots to have a repertoire of skills applicable to a wide range of circumstances. When using learning-based methods to acquire such skills, the key challenge is to obtain training data that covers diverse and feasible variations of the task, which often requires non-trivial manual labor and domain knowledge. In this work, we introduce Active Task Randomization (ATR), an approach that learns robust skills through the unsupervised generation of training tasks. ATR selects suitable tasks, which consist of an initial environment state and manipulation goal, for learning robust skills by balancing the diversity and feasibility of the tasks. We propose to predict task diversity and feasibility by jointly learning a compact task representation. The selected tasks are then procedurally generated in simulation using graph-based parameterization. The active selection of these training tasks enables skill policies trained with our framework to robustly handle a diverse range of objects and arrangements at test time. We demonstrate that the learned skills can be composed by a task planner to solve unseen sequential manipulation problems based on visual inputs. Compared to baseline methods, ATR can achieve superior success rates in single-step and sequential manipulation tasks.