Continual Reinforcement Learning by Planning with Online World Models

• URL: http://arxiv.org/abs/2507.09177v1
• Date: Sat, 12 Jul 2025 07:52:31 GMT
• Title: Continual Reinforcement Learning by Planning with Online World Models
• Authors: Zichen Liu, Guoji Fu, Chao Du, Wee Sun Lee, Min Lin,
• Abstract summary: Continual reinforcement learning (CRL) refers to a naturalistic setting where an agent needs to endlessly evolve, by trial and error, to solve multiple tasks that are presented sequentially.<n>One of the largest obstacles to CRL is that the agent may forget how to solve previous tasks when learning a new task, known as catastrophic forgetting.<n>We propose to address this challenge by planning with online world models. Specifically, we learn a Follow-The-Leader shallow model online to capture the world dynamics, in which we plan using model predictive control to solve a set of tasks specified by any reward functions.
• Score: 29.730338886371776
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Continual reinforcement learning (CRL) refers to a naturalistic setting where an agent needs to endlessly evolve, by trial and error, to solve multiple tasks that are presented sequentially. One of the largest obstacles to CRL is that the agent may forget how to solve previous tasks when learning a new task, known as catastrophic forgetting. In this paper, we propose to address this challenge by planning with online world models. Specifically, we learn a Follow-The-Leader shallow model online to capture the world dynamics, in which we plan using model predictive control to solve a set of tasks specified by any reward functions. The online world model is immune to forgetting by construction with a proven regret bound of $\mathcal{O}(\sqrt{K^2D\log(T)})$ under mild assumptions. The planner searches actions solely based on the latest online model, thus forming a FTL Online Agent (OA) that updates incrementally. To assess OA, we further design Continual Bench, a dedicated environment for CRL, and compare with several strong baselines under the same model-planning algorithmic framework. The empirical results show that OA learns continuously to solve new tasks while not forgetting old skills, outperforming agents built on deep world models with various continual learning techniques.

Related papers

• Intention-Conditioned Flow Occupancy Models [69.79049994662591]
  Large-scale pre-training has fundamentally changed how machine learning research is done today.<n>Applying this same framework to reinforcement learning is appealing because it offers compelling avenues for addressing core challenges in RL.<n>Recent advances in generative AI have provided new tools for modeling highly complex distributions.
  arXiv  Detail & Related papers  (2025-06-10T15:27:46Z)
• Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models [31.509112804985133]
  Reinforcement learning (RL) learns policies through trial and error, and optimal control, which plans actions using a learned or known dynamics model.<n>We systematically analyze the performance of different RL and control-based methods under datasets of varying quality.<n>Our results show that model-free RL excels when abundant, high-quality data is available, while model-based planning excels in generalization to novel environment layouts, trajectory stitching, and data-efficiency.
  arXiv  Detail & Related papers  (2025-02-20T18:39:41Z)
• Integrating Reinforcement Learning, Action Model Learning, and Numeric Planning for Tackling Complex Tasks [12.281688043929996]
  Automated Planning algorithms require a model of the domain that specifies the preconditions and effects of each action.<n>It remains unclear whether learning a numeric domain model and planning is an effective approach for numeric planning environments.<n>In this work, we explore the benefits of learning a numeric domain model and compare it with alternative model-free solutions.
  arXiv  Detail & Related papers  (2025-02-18T16:26:21Z)
• Continual Diffuser (CoD): Mastering Continual Offline Reinforcement Learning with Experience Rehearsal [54.93261535899478]
  In real-world applications, such as robotic control of reinforcement learning, the tasks are changing, and new tasks arise in a sequential order.<n>This situation poses the new challenge of plasticity-stability trade-off for training an agent who can adapt to task changes and retain acquired knowledge.<n>We propose a rehearsal-based continual diffusion model, called Continual diffuser (CoD), to endow the diffuser with the capabilities of quick adaptation (plasticity) and lasting retention (stability)
  arXiv  Detail & Related papers  (2024-09-04T08:21:47Z)
• Distributional Successor Features Enable Zero-Shot Policy Optimization [36.53356539916603]
  This work proposes a novel class of models, i.e., Distributional Successor Features for Zero-Shot Policy Optimization (DiSPOs)<n>DiSPOs learn a distribution of successor features of a stationary dataset's behavior policy, along with a policy that acts to realize different successor features achievable within the dataset.<n>By directly modeling long-term outcomes in the dataset, DiSPOs avoid compounding error while enabling a simple scheme for zero-shot policy optimization across reward functions.
  arXiv  Detail & Related papers  (2024-03-10T22:27:21Z)
• MOTO: Offline Pre-training to Online Fine-tuning for Model-based Robot Learning [52.101643259906915]
  We study the problem of offline pre-training and online fine-tuning for reinforcement learning from high-dimensional observations. Existing model-based offline RL methods are not suitable for offline-to-online fine-tuning in high-dimensional domains. We propose an on-policy model-based method that can efficiently reuse prior data through model-based value expansion and policy regularization.
  arXiv  Detail & Related papers  (2024-01-06T21:04:31Z)
• Finetuning Offline World Models in the Real World [13.46766121896684]
  Reinforcement Learning (RL) is notoriously data-inefficient, which makes training on a real robot difficult. offline RL has been proposed as a framework for training RL policies on pre-existing datasets without any online interaction. In this work, we consider the problem of pretraining a world model with offline data collected on a real robot, and then finetuning the model on online data collected by planning with the learned model.
  arXiv  Detail & Related papers  (2023-10-24T17:46:12Z)
• Continual Visual Reinforcement Learning with A Life-Long World Model [55.05017177980985]
  We present a new continual learning approach for visual dynamics modeling.<n>We first introduce the life-long world model, which learns task-specific latent dynamics.<n>Then, we address the value estimation challenge for previous tasks with the exploratory-conservative behavior learning approach.
  arXiv  Detail & Related papers  (2023-03-12T05:08:03Z)
• On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning [45.73223325256312]
  We investigate whether internal models learned by modern model-based RL algorithms can be leveraged to solve new, distinctly different tasks faster. We propose Model-Based Cross-Task Transfer (XTRA), a framework for sample-efficient online RL with scalable pretraining and finetuning of learned world models.
  arXiv  Detail & Related papers  (2022-10-19T17:57:06Z)
• Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels [112.63440666617494]
  Reinforcement learning algorithms can succeed but require large amounts of interactions between the agent and the environment. We propose a new method to solve it, using unsupervised model-based RL, for pre-training the agent. We show robust performance on the Real-Word RL benchmark, hinting at resiliency to environment perturbations during adaptation.
  arXiv  Detail & Related papers  (2022-09-24T14:22:29Z)
• World Model as a Graph: Learning Latent Landmarks for Planning [12.239590266108115]
  Planning is a hallmark of human intelligence. One prominent framework, Model-Based RL, learns a world model and plans using step-by-step virtual rollouts. We propose to learn graph-structured world models composed of sparse, multi-step transitions.
  arXiv  Detail & Related papers  (2020-11-25T02:49:21Z)
• Goal-Aware Prediction: Learning to Model What Matters [105.43098326577434]
  One of the fundamental challenges in using a learned forward dynamics model is the mismatch between the objective of the learned model and that of the downstream planner or policy. We propose to direct prediction towards task relevant information, enabling the model to be aware of the current task and encouraging it to only model relevant quantities of the state space. We find that our method more effectively models the relevant parts of the scene conditioned on the goal, and as a result outperforms standard task-agnostic dynamics models and model-free reinforcement learning.
  arXiv  Detail & Related papers  (2020-07-14T16:42:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.