# Self-Supervised Curriculum Generation for Autonomous Reinforcement Learning without Task-Specific Knowledge

arXiv: https://arxiv.org/abs/2311.09195 · HTML: https://mlsanity.com/paper/2311.09195/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 33 references that are in the map.
- First posted on arXiv 15 Nov 2023.

## Builds on (most cited first, 26 of 26)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [End-to-End Training of Deep Visuomotor Policies](https://mlsanity.com/paper/1504.00702/) (2015)
- [Learning Dexterous In-Hand Manipulation](https://mlsanity.com/paper/1808.00177/) (2018)
- [A systematic study of the class imbalance problem in convolutional neural networks](https://mlsanity.com/paper/1710.05381/) (2017)
- [Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection](https://mlsanity.com/paper/1603.02199/) (2016)
- [MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale](https://mlsanity.com/paper/2104.08212/) (2021)
- [Deep Dynamics Models for Learning Dexterous Manipulation](https://mlsanity.com/paper/1909.11652/) (2019)
- [TossingBot: Learning to Throw Arbitrary Objects with Residual Physics](https://mlsanity.com/paper/1903.11239/) (2019)
- [The Ingredients of Real-World Robotic Reinforcement Learning](https://mlsanity.com/paper/2004.12570/) (2020)
- [Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning](https://mlsanity.com/paper/1711.06782/) (2017)
- [Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost](https://mlsanity.com/paper/1810.06045/) (2018)
- [ROBEL: Robotics Benchmarks for Learning with Low-Cost Robots](https://mlsanity.com/paper/1909.11639/) (2019)
- [Autonomous Reinforcement Learning via Subgoal Curricula](https://mlsanity.com/paper/2107.12931/) (2021)
- [Autonomous Reinforcement Learning: Formalism and Benchmarking](https://mlsanity.com/paper/2112.09605/) (2021)
- [Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning](https://mlsanity.com/paper/2004.12974/) (2020)
- [Continual Learning of Control Primitives: Skill Discovery via Reset-Games](https://mlsanity.com/paper/2011.05286/) (2020)
- [Collective Robot Reinforcement Learning with Distributed Asynchronous Guided Policy Search](https://mlsanity.com/paper/1610.00673/) (2016)
- [Automating Reinforcement Learning with Example-based Resets](https://mlsanity.com/paper/2204.02041/) (2022)

## Built on by (most cited first, 1 of 1)

- [Autonomous Algorithm for Training Autonomous Vehicles with Minimal Human Intervention](https://mlsanity.com/paper/2405.13345/) (2024)

## Abstract (arXiv)

A significant bottleneck in applying current reinforcement learning algorithms to real-world scenarios is the need to reset the environment between every episode. This reset process demands substantial human intervention, making it difficult for the agent to learn continuously and autonomously. Several recent works have introduced autonomous reinforcement learning (ARL) algorithms that generate curricula for jointly training reset and forward policies. While their curricula can reduce the number of required manual resets by taking into account the agent's learning progress, they rely on task-specific knowledge, such as predefined initial states or reset reward functions. In this paper, we propose a novel ARL algorithm that can generate a curriculum adaptive to the agent's learning progress without task-specific knowledge. Our curriculum empowers the agent to autonomously reset to diverse and informative initial states. To achieve this, we introduce a success discriminator that estimates the success probability from each initial state when the agent follows the forward policy. The success discriminator is trained with relabeled transitions in a self-supervised manner. Our experimental results demonstrate that our ARL algorithm can generate an adaptive curriculum and enable the agent to efficiently bootstrap to solve sparse-reward maze navigation and manipulation tasks, outperforming baselines with significantly fewer manual resets.