# Preparing for the Unknown: Learning a Universal Policy with Online System Identification

arXiv: https://arxiv.org/abs/1702.02453 · HTML: https://mlsanity.com/paper/1702.02453/

## Key facts

- Cited by 141 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Feb 2017.

## Built on by (most cited first, 30 of 141)

- [RMA: Rapid Motor Adaptation for Legged Robots](https://mlsanity.com/paper/2107.04034/) (2021)
- [How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned](https://mlsanity.com/paper/2102.02915/) (2021)
- [Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI](https://mlsanity.com/paper/2407.06886/) (2024)
- [GNM: A General Navigation Model to Drive Any Robot](https://mlsanity.com/paper/2210.03370/) (2022)
- [A Survey of Zero-shot Generalisation in Deep Reinforcement Learning](https://mlsanity.com/paper/2111.09794/) (2021)
- [Legged Locomotion in Challenging Terrains using Egocentric Vision](https://mlsanity.com/paper/2211.07638/) (2022)
- [ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills](https://mlsanity.com/paper/2502.01143/) (2025)
- [Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotion](https://mlsanity.com/paper/2210.10044/) (2022)
- [Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviation](https://mlsanity.com/paper/2408.11812/) (2024)
- [DrEureka: Language Model Guided Sim-To-Real Transfer](https://mlsanity.com/paper/2406.01967/) (2024)
- [Minimizing Energy Consumption Leads to the Emergence of Gaits in Legged Robots](https://mlsanity.com/paper/2111.01674/) (2021)
- [Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination](https://mlsanity.com/paper/2112.11701/) (2021)
- [A Survey on Model-based Reinforcement Learning](https://mlsanity.com/paper/2206.09328/) (2022)
- [Robot Learning from Randomized Simulations: A Review](https://mlsanity.com/paper/2111.00956/) (2021)
- [When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning](https://mlsanity.com/paper/2206.13464/) (2022)
- [How Simulation Helps Autonomous Driving:A Survey of Sim2real, Digital Twins, and Parallel Intelligence](https://mlsanity.com/paper/2305.01263/) (2023)
- [AdaAfford: Learning to Adapt Manipulation Affordance for 3D Articulated Objects via Few-shot Interactions](https://mlsanity.com/paper/2112.00246/) (2021)
- [Adapting Rapid Motor Adaptation for Bipedal Robots](https://mlsanity.com/paper/2205.15299/) (2022)
- [Coupling Vision and Proprioception for Navigation of Legged Robots](https://mlsanity.com/paper/2112.02094/) (2021)
- [Auto-Tuned Sim-to-Real Transfer](https://mlsanity.com/paper/2104.07662/) (2021)
- [AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning](https://mlsanity.com/paper/2107.02729/) (2021)
- [GenLoco: Generalized Locomotion Controllers for Quadrupedal Robots](https://mlsanity.com/paper/2209.05309/) (2022)
- [Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment](https://mlsanity.com/paper/2104.05632/) (2021)
- [Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability](https://mlsanity.com/paper/2209.08025/) (2022)
- [Cross-Domain Policy Adaptation via Value-Guided Data Filtering](https://mlsanity.com/paper/2305.17625/) (2023)
- [Unsupervised Visual Attention and Invariance for Reinforcement Learning](https://mlsanity.com/paper/2104.02921/) (2021)
- [QuestEnvSim: Environment-Aware Simulated Motion Tracking from Sparse Sensors](https://mlsanity.com/paper/2306.05666/) (2023)
- [Polybot: Training One Policy Across Robots While Embracing Variability](https://mlsanity.com/paper/2307.03719/) (2023)
- [HuB: Learning Extreme Humanoid Balance](https://mlsanity.com/paper/2505.07294/) (2025)
- [Context is Everything: Implicit Identification for Dynamics Adaptation](https://mlsanity.com/paper/2203.05549/) (2022)

## Abstract (arXiv)

We present a new method of learning control policies that successfully operate under unknown dynamic models. We create such policies by leveraging a large number of training examples that are generated using a physical simulator. Our system is made of two components: a Universal Policy (UP) and a function for Online System Identification (OSI). We describe our control policy as universal because it is trained over a wide array of dynamic models. These variations in the dynamic model may include differences in mass and inertia of the robots' components, variable friction coefficients, or unknown mass of an object to be manipulated. By training the Universal Policy with this variation, the control policy is prepared for a wider array of possible conditions when executed in an unknown environment. The second part of our system uses the recent state and action history of the system to predict the dynamics model parameters mu. The value of mu from the Online System Identification is then provided as input to the control policy (along with the system state). Together, UP-OSI is a robust control policy that can be used across a wide range of dynamic models, and that is also responsive to sudden changes in the environment. We have evaluated the performance of this system on a variety of tasks, including the problem of cart-pole swing-up, the double inverted pendulum, locomotion of a hopper, and block-throwing of a manipulator. UP-OSI is effective at these tasks across a wide range of dynamic models. Moreover, when tested with dynamic models outside of the training range, UP-OSI outperforms the Universal Policy alone, even when UP is given the actual value of the model dynamics. In addition to the benefits of creating more robust controllers, UP-OSI also holds out promise of narrowing the Reality Gap between simulated and real physical systems.