# Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning

arXiv: https://arxiv.org/abs/2303.01488 · HTML: https://mlsanity.com/paper/2303.01488/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 61 references that are in the map.
- First posted on arXiv 2 Mar 2023.

## Builds on (most cited first, 30 of 54)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [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)
- [CURL: Contrastive Unsupervised Representations for Reinforcement Learning](https://mlsanity.com/paper/2004.04136/) (2020)
- [QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation](https://mlsanity.com/paper/1806.10293/) (2018)
- [Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations](https://mlsanity.com/paper/1709.10087/) (2017)
- [BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning](https://mlsanity.com/paper/2202.02005/) (2022)
- [f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization](https://mlsanity.com/paper/1606.00709/) (2016)
- [Learning Robust Rewards with Adversarial Inverse Reinforcement Learning](https://mlsanity.com/paper/1710.11248/) (2017)
- [Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization](https://mlsanity.com/paper/1603.00448/) (2016)
- [Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning](https://mlsanity.com/paper/2107.09645/) (2021)
- [Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates](https://mlsanity.com/paper/1610.00633/) (2016)
- [Overcoming Exploration in Reinforcement Learning with Demonstrations](https://mlsanity.com/paper/1709.10089/) (2017)
- [Randomized Ensembled Double Q-Learning: Learning Fast Without a Model](https://mlsanity.com/paper/2101.05982/) (2021)
- [Deep Visual Foresight for Planning Robot Motion](https://mlsanity.com/paper/1610.00696/) (2016)
- [Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model](https://mlsanity.com/paper/1907.00953/) (2019)
- [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)
- [Deep Dynamics Models for Learning Dexterous Manipulation](https://mlsanity.com/paper/1909.11652/) (2019)
- [Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning](https://mlsanity.com/paper/1809.02925/) (2018)
- [A Divergence Minimization Perspective on Imitation Learning Methods](https://mlsanity.com/paper/1911.02256/) (2019)
- [Learning to Walk via Deep Reinforcement Learning](https://mlsanity.com/paper/1812.11103/) (2018)
- [Learning to Poke by Poking: Experiential Learning of Intuitive Physics](https://mlsanity.com/paper/1606.07419/) (2016)
- [Deep Spatial Autoencoders for Visuomotor Learning](https://mlsanity.com/paper/1509.06113/) (2015)

## Built on by (most cited first, 30 of 34)

- [π*0.6: a VLA That Learns From Experience](https://mlsanity.com/paper/2511.14759/) (2025)
- [SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning](https://mlsanity.com/paper/2401.16013/) (2024)
- [Self-Improving Vision-Language-Action Models with Data Generation via Residual RL](https://mlsanity.com/paper/2511.00091/) (2025)
- [Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learning](https://mlsanity.com/paper/2310.15145/) (2023)
- [GR-RL: Going Dexterous and Precise for Long-Horizon Robotic Manipulation](https://mlsanity.com/paper/2512.01801/) (2025)
- [Autonomous Improvement of Instruction Following Skills via Foundation Models](https://mlsanity.com/paper/2407.20635/) (2024)
- [Affordance-Guided Reinforcement Learning via Visual Prompting](https://mlsanity.com/paper/2407.10341/) (2024)
- [Continuously Improving Mobile Manipulation with Autonomous Real-World RL](https://mlsanity.com/paper/2409.20568/) (2024)
- [So You Think You Can Scale Up Autonomous Robot Data Collection?](https://mlsanity.com/paper/2411.01813/) (2024)
- [REBOOT: Reuse Data for Bootstrapping Efficient Real-World Dexterous Manipulation](https://mlsanity.com/paper/2309.03322/) (2023)
- [Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfer](https://mlsanity.com/paper/2512.01061/) (2025)
- [VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon](https://mlsanity.com/paper/2607.01804/) (2026)
- [Autonomous Robotic Reinforcement Learning with Asynchronous Human Feedback](https://mlsanity.com/paper/2310.20608/) (2023)
- [Robot Learning with Super-Linear Scaling](https://mlsanity.com/paper/2412.01770/) (2024)
- [The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement](https://mlsanity.com/paper/2609.11873/) (2026)
- [From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning](https://mlsanity.com/paper/2603.10263/) (2026)
- [ViVa: A Video-Generative Value Model for Robot Reinforcement Learning](https://mlsanity.com/paper/2604.08168/) (2026)
- [ALOE: Action-Level Off-Policy Evaluation for Vision-Language-Action Model Post-Training](https://mlsanity.com/paper/2602.12691/) (2026)
- [SafeMimic: Towards Safe and Autonomous Human-to-Robot Imitation for Mobile Manipulation](https://mlsanity.com/paper/2506.15847/) (2025)
- [Intelligent Switching for Reset-Free RL](https://mlsanity.com/paper/2405.01684/) (2024)
- [A Backbone for Long-Horizon Robot Task Understanding](https://mlsanity.com/paper/2408.01334/) (2024)
- [When Learning Is Out of Reach, Reset: Generalization in Autonomous Visuomotor Reinforcement Learning](https://mlsanity.com/paper/2303.17600/) (2023)
- [Reset-free Reinforcement Learning with World Models](https://mlsanity.com/paper/2408.09807/) (2024)
- [Bifrost: Steering Strategic Trajectories to Bridge Contextual Gaps for Self-Improving Agents](https://mlsanity.com/paper/2602.05810/) (2026)
- [Scaling Sim-to-Real VLA Reinforcement Learning with Generative 3D Worlds](https://mlsanity.com/paper/2603.18532/) (2026)
- [Reinforcement Learning for Real-Time Vision-Language-Action Policies](https://mlsanity.com/paper/2609.18207/) (2026)
- [Efficient Sparse-Reward Goal-Conditioned Reinforcement Learning with a High Replay Ratio and Regularization](https://mlsanity.com/paper/2312.05787/) (2023)
- [Real-Time Reinforcement Learning for Dynamic Tasks with a Parallel Soft Robot](https://mlsanity.com/paper/2509.19525/) (2025)
- [AutoDex: An Automated Real-World System for Dexterous Grasping Data Collection](https://mlsanity.com/paper/2606.23689/) (2026)
- [Find Something You Can't Do: Agentic Real-World Reinforcement Learning for Self-Improving VLA Models](https://mlsanity.com/paper/2609.32069/) (2026)

## Abstract (arXiv)

In imitation and reinforcement learning, the cost of human supervision limits the amount of data that robots can be trained on. An aspirational goal is to construct self-improving robots: robots that can learn and improve on their own, from autonomous interaction with minimal human supervision or oversight. Such robots could collect and train on much larger datasets, and thus learn more robust and performant policies. While reinforcement learning offers a framework for such autonomous learning via trial-and-error, practical realizations end up requiring extensive human supervision for reward function design and repeated resetting of the environment between episodes of interactions. In this work, we propose MEDAL++, a novel design for self-improving robotic systems: given a small set of expert demonstrations at the start, the robot autonomously practices the task by learning to both do and undo the task, simultaneously inferring the reward function from the demonstrations. The policy and reward function are learned end-to-end from high-dimensional visual inputs, bypassing the need for explicit state estimation or task-specific pre-training for visual encoders used in prior work. We first evaluate our proposed algorithm on a simulated non-episodic benchmark EARL, finding that MEDAL++ is both more data efficient and gets up to 30% better final performance compared to state-of-the-art vision-based methods. Our real-robot experiments show that MEDAL++ can be applied to manipulation problems in larger environments than those considered in prior work, and autonomous self-improvement can improve the success rate by 30-70% over behavior cloning on just the expert data. Code, training and evaluation videos along with a brief overview is available at: https://architsharma97.github.io/self-improving-robots/