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

TL;DR

This paper introduces AGWM, a world model that explicitly tracks action prerequisites as a DAG to improve multi-step predictions and generalization in environments with dynamic action affordances.

Contribution

The paper proposes AGWM, a novel affordance-grounded world model that captures dynamic action prerequisites using a DAG structure, addressing limitations of standard models.

Findings

Lower multi-step prediction error in experiments

Better generalization to novel configurations

Enhanced interpretability of action dependencies

Abstract

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.