Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

AGWM: Affordance-Grounded World Models for Environments with Compositional Prerequisites

About

In model-based learning, the agent learns behaviors by simulating trajectories based on world model predictions. Standard world models typically learn a stationary transition function that maps states and actions to next states, when an action and an outcome frequently co-occur in training data, the model tends to internalize this correlation as a general causal rule while ignoring action preconditions. In interactive environments, however, agent actions can reshape the future affordance space. At each timestep, an action may becomes executable only after its prerequisites are met, or non-executable when they are destroyed. We term such events structure-changing events (SC events). As a result, a conventional world model often fails to determine whether a given action is executable in the current state, especially in multi-step predictions. Each imagined step is conditioned on an incorrect affordance state, and therefore the prediction error compounds over the rollout horizon. In this paper, we propose AGWM (Affordance-Grounded World Model), which learns an abstract affordance structure represented as a DAG of prerequisite dependencies to explicitly track the dynamic executability of actions. Experiments on game-based simulated environments demonstrate the effectiveness of our method by achieving lower multi-step prediction error, better generalization to novel configurations, and improved interpretability.

Qinshi Zhang, Weipeng Deng, Zhihan Jiang, Jiaming Qu, Qianren Li, Weitao Xu, Ray LC (5) __INSTITUTION_7__ University of California, San Diego, (2) University of Hong Kong, (3) Columbia University, (4) Amazon, (5) City University of Hong Kong)• 2026

Related benchmarks

TaskDatasetResultRank
World Model PredictionKeyDungeon
Imagination MSE (Avg)5.63
2
World Model PredictionForage
Imagination MSE (Avg)6.95
2
World Model PredictionHarvest
Imagination MSE (Avg)21.19
2
World Model PredictionMiniHack
Average Imagination MSE1.02e+3
2
World Model PredictionRelay
Imagination MSE (Avg)6.11
2
World Model PredictionCascade
Average Imagination MSE16.78
2
World Model PredictionCrafter
Avg Imagination MSE5.56
2
World Model PredictionCraftax
Average Imagination MSE0.0894
2
Showing 8 of 8 rows

Other info

Follow for update