# Changepoint-Aware World Models: Detecting Dynamics Shifts and Recovering by Forgetting Stale Replay in Model-Based RL

arXiv: https://arxiv.org/abs/2609.18950 · HTML: https://mlsanity.com/paper/2609.18950/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Embodied and robot world models, one of 11 directions in World models.
- Builds on 24 of its 29 references that are in the map.
- First posted on arXiv 15 Jul 2026.

## Placed in

- World models / [Embodied and robot world models](https://mlsanity.com/wm/embodied-and-robot-world-models/)

## Builds on (most cited first, 24 of 24)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [DeepMind Control Suite](https://mlsanity.com/paper/1801.00690/) (2018)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models](https://mlsanity.com/paper/1805.12114/) (2018)
- [RMA: Rapid Motor Adaptation for Legged Robots](https://mlsanity.com/paper/2107.04034/) (2021)
- [Temporal Difference Learning for Model Predictive Control](https://mlsanity.com/paper/2203.04955/) (2022)
- [Planning to Explore via Self-Supervised World Models](https://mlsanity.com/paper/2005.05960/) (2020)
- [Towards Continual Reinforcement Learning: A Review and Perspectives](https://mlsanity.com/paper/2012.13490/) (2020)
- [The Primacy Bias in Deep Reinforcement Learning](https://mlsanity.com/paper/2205.07802/) (2022)
- [Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments](https://mlsanity.com/paper/1710.03641/) (2017)
- [A Definition of Continual Reinforcement Learning](https://mlsanity.com/paper/2307.11046/) (2023)
- [The Value Equivalence Principle for Model-Based Reinforcement Learning](https://mlsanity.com/paper/2011.03506/) (2020)
- [Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizations](https://mlsanity.com/paper/1308.3513/) (2013)
- [Minimum-Delay Adaptation in Non-Stationary Reinforcement Learning via Online High-Confidence Change-Point Detection](https://mlsanity.com/paper/2105.09452/) (2021)
- [An Adaptive Deep RL Method for Non-Stationary Environments with Piecewise Stable Context](https://mlsanity.com/paper/2212.12735/) (2022)
- [Novelty Detection in Reinforcement Learning with World Models](https://mlsanity.com/paper/2310.08731/) (2023)
- [A Behavior-Aware Approach for Deep Reinforcement Learning in Non-stationary Environments without Known Change Points](https://mlsanity.com/paper/2405.14214/) (2024)
- [ARCADE: Adaptive Robot Control with Online Changepoint-Aware Bayesian Dynamics Learning](https://mlsanity.com/paper/2512.14331/) (2025)

## Abstract (arXiv)

A robot's learned model of its own dynamics is only valid until those dynamics change: actuators wear, payloads shift, and joints stiffen. A model-based agent that keeps training as if nothing happened adapts slowly, dragged back by a replay buffer full of stale experience. We present Changepoint-Aware World Models (CAWM), a DreamerV3 agent that detects an abrupt dynamics shift from its own internal prediction error, using an online CUSUM test against a rolling baseline that fires only on abrupt change rather than on slow learning drift. It then forgets stale replay, keeping the learned representation while flushing obsolete data. On simulated locomotion under two robot-relevant shifts, doubled gravity and halved actuator gain, CAWM recovers substantially faster than passive retraining. It also beats a strong baseline that respawns a fresh dynamics model on detection, the deep-world-model analogue of model-bank methods. With the response triggered at the shift, CAWM gains +95 to +153 return in the first 30k post-shift frames over three seeds, while matching that respawn at asymptote. Running the detector in closed loop reproduces this gain on the gravity shift. The benefit holds across both shift types, and is largest when the shift is severe enough that old data is genuinely obsolete.