AXIOM: Learning To Play Games In Minutes With Expanding Object-centric Models

Abstract

Current deep reinforcement learning (DRL) approaches achieve state-of-the-art performance in various domains, but struggle with data efficiency compared to human learning, which leverages core priors about objects and their interactions. Active inference offers a principled framework for integrating sensory information with prior knowledge to learn a world model and quantify the uncertainty of its own beliefs and predictions. However, active inference models are usually crafted for a single task with bespoke knowledge, so they lack the domain flexibility typical of DRL approaches. To bridge this gap, we propose a novel architecture that integrates a minimal yet expressive set of core priors about object-centric dynamics and interactions to accelerate learning in low-data regimes. The resulting approach, which we call AXIOM, combines the usual data efficiency and interpretability of Bayesian approaches with the across-task generalization usually associated with DRL. AXIOM represents sce

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyheins2025axiom

Related papers

• R-AIF: Solving Sparse-reward Robotic Tasks From Pixels With Active Inference And World Models (2024)4.52
• COBRA: Data-efficient Model-based RL Through Unsupervised Object Discovery And Curiosity-driven Exploration (2019)0.00
• Aixijs: A Software Demo For General Reinforcement Learning (2017)0.00
• Active Inference And Reinforcement Learning: A Unified Inference On Continuous State And Action Spaces Under Partial Observability (2022)5.84
• Deep Active Inference For Partially Observable Mdps (2020)9.59
• Dynamic Action Interpolation: A Universal Approach For Accelerating Reinforcement Learning With Expert Guidance (2025)0.00
• Active Inference: Demystified And Compared (2019)15.98
• Simplified Action Decoder For Deep Multi-agent Reinforcement Learning (2019)4.03