# When to Update Your Model: Constrained Model-based Reinforcement Learning

arXiv: https://arxiv.org/abs/2210.08349 · HTML: https://mlsanity.com/paper/2210.08349/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 62 references that are in the map.
- First posted on arXiv 15 Oct 2022.

## Builds on (most cited first, 30 of 31)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [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)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [End-to-End Training of Deep Visuomotor Policies](https://mlsanity.com/paper/1504.00702/) (2015)
- [Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models](https://mlsanity.com/paper/1805.12114/) (2018)
- [When to Trust Your Model: Model-Based Policy Optimization](https://mlsanity.com/paper/1906.08253/) (2019)
- [MOPO: Model-based Offline Policy Optimization](https://mlsanity.com/paper/2005.13239/) (2020)
- [Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning](https://mlsanity.com/paper/1708.02596/) (2017)
- [Model-Ensemble Trust-Region Policy Optimization](https://mlsanity.com/paper/1802.10592/) (2018)
- [Differentiable MPC for End-to-end Planning and Control](https://mlsanity.com/paper/1810.13400/) (2018)
- [Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion](https://mlsanity.com/paper/1807.01675/) (2018)
- [Benchmarking Model-Based Reinforcement Learning](https://mlsanity.com/paper/1907.02057/) (2019)
- [Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning](https://mlsanity.com/paper/1803.00101/) (2018)
- [Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees](https://mlsanity.com/paper/1807.03858/) (2018)
- [Model-Based Reinforcement Learning with a Generative Model is Minimax Optimal](https://mlsanity.com/paper/1906.03804/) (2019)
- [Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model](https://mlsanity.com/paper/2005.12900/) (2020)
- [Lipschitz Continuity in Model-based Reinforcement Learning](https://mlsanity.com/paper/1804.07193/) (2018)
- [Information Theoretic Regret Bounds for Online Nonlinear Control](https://mlsanity.com/paper/2006.12466/) (2020)
- [ROBEL: Robotics Benchmarks for Learning with Low-Cost Robots](https://mlsanity.com/paper/1909.11639/) (2019)
- [PyRep: Bringing V-REP to Deep Robot Learning](https://mlsanity.com/paper/1906.11176/) (2019)
- [MBRL-Lib: A Modular Library for Model-based Reinforcement Learning](https://mlsanity.com/paper/2104.10159/) (2021)
- [Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies](https://mlsanity.com/paper/1905.11527/) (2019)
- [Trust the Model When It Is Confident: Masked Model-based Actor-Critic](https://mlsanity.com/paper/2010.04893/) (2020)
- [Dual Policy Iteration](https://mlsanity.com/paper/1805.10755/) (2018)
- [Near-Optimal Time and Sample Complexities for Solving Discounted Markov Decision Process with a Generative Model](https://mlsanity.com/paper/1806.01492/) (2018)
- [Model-based Reinforcement Learning for Continuous Control with Posterior Sampling](https://mlsanity.com/paper/2012.09613/) (2020)

## Built on by (most cited first, 14 of 14)

- [Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic](https://mlsanity.com/paper/2306.02865/) (2023)
- [Trust the Model Where It Trusts Itself -- Model-Based Actor-Critic with Uncertainty-Aware Rollout Adaption](https://mlsanity.com/paper/2405.19014/) (2024)
- [Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL](https://mlsanity.com/paper/2405.18520/) (2024)
- [Mind the Model, Not the Agent: The Primacy Bias in Model-based RL](https://mlsanity.com/paper/2310.15017/) (2023)
- [How to Fine-tune the Model: Unified Model Shift and Model Bias Policy Optimization](https://mlsanity.com/paper/2309.12671/) (2023)
- [Learning to Play Atari in a World of Tokens](https://mlsanity.com/paper/2406.01361/) (2024)
- [OMPO: A Unified Framework for RL under Policy and Dynamics Shifts](https://mlsanity.com/paper/2405.19080/) (2024)
- [Model-Based Reinforcement Learning with Isolated Imaginations](https://mlsanity.com/paper/2303.14889/) (2023)
- [Efficient Cross-Domain Offline Reinforcement Learning with Dynamics- and Value-Aligned Data Filtering](https://mlsanity.com/paper/2512.02435/) (2025)
- [Measuring the Value of World-Model Updates: A Counterfactual Utility Protocol for Continual Adaptation](https://mlsanity.com/paper/2609.10954/) (2026)
- [Scrutinize What We Ignore: Reining In Task Representation Shift Of Context-Based Offline Meta Reinforcement Learning](https://mlsanity.com/paper/2405.12001/) (2024)
- [RoboGolf: Mastering Real-World Minigolf with a Reflective Multi-Modality Vision-Language Model](https://mlsanity.com/paper/2406.10157/) (2024)
- [Dual Alignment Maximin Optimization for Offline Model-based RL](https://mlsanity.com/paper/2502.00850/) (2025)
- [Model-Based Reinforcement Learning for Heterogeneous Multi-Robot Task Assignment Under Distribution Shifts](https://mlsanity.com/paper/2608.21554/) (2026)

## Abstract (arXiv)

Designing and analyzing model-based RL (MBRL) algorithms with guaranteed monotonic improvement has been challenging, mainly due to the interdependence between policy optimization and model learning. Existing discrepancy bounds generally ignore the impacts of model shifts, and their corresponding algorithms are prone to degrade performance by drastic model updating. In this work, we first propose a novel and general theoretical scheme for a non-decreasing performance guarantee of MBRL. Our follow-up derived bounds reveal the relationship between model shifts and performance improvement. These discoveries encourage us to formulate a constrained lower-bound optimization problem to permit the monotonicity of MBRL. A further example demonstrates that learning models from a dynamically-varying number of explorations benefit the eventual returns. Motivated by these analyses, we design a simple but effective algorithm CMLO (Constrained Model-shift Lower-bound Optimization), by introducing an event-triggered mechanism that flexibly determines when to update the model. Experiments show that CMLO surpasses other state-of-the-art methods and produces a boost when various policy optimization methods are employed.