ORACLE: Orchestrate NPC Daily Activities using Contrastive Learning with Transformer-CVAE

2026-03-25

AI Summary

Existing methods for generating daily activities of non-player characters (NPCs) often produce monotonous behaviors that fail to capture the complexity and diversity of human routines. To address this limitation, this work proposes a novel architecture that integrates Transformers, conditional variational autoencoders (CVAEs), and contrastive learning—introducing contrastive learning into the Transformer-CVAE framework for the first time. The model learns from the CASAS smart home dataset to synthesize high-fidelity, diverse indoor activity sequences. By leveraging contrastive learning, the approach effectively mitigates challenges such as data imbalance, limited sample availability, and the absence of suitable pre-trained models. Experimental results demonstrate that the proposed method significantly outperforms existing approaches in terms of generation fidelity, controllability, and generalization capability.

Technology Category

• Natural Language Processing: Generation
• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

The integration of Non-player characters (NPCs) within digital environments has been increasingly recognized for its potential to augment user immersion and cognitive engagement. The sophisticated orchestration of their daily activities, reflecting the nuances of human daily routines, contributes significantly to the realism of digital environments. Nevertheless, conventional approaches often produce monotonous repetition, falling short of capturing the intricacies of real human activity plans. In response to this, we introduce ORACLE, a novel generative model for the synthesis of realistic indoor daily activity plans, ensuring NPCs' authentic presence in digital habitats. Exploiting the CASAS smart home dataset's 24-hour indoor activity sequences, ORACLE addresses challenges in the dataset, including its imbalanced sequential data, the scarcity of training samples, and the absence of pre-trained models encapsulating human daily activity patterns. ORACLE's training leverages the sequential data processing prowess of Transformers, the generative controllability of Conditional Variational Autoencoders (CVAE), and the discriminative refinement of contrastive learning. Our experimental results validate the superiority of generating NPC activity plans and the efficacy of our design strategies over existing methods.

Problem

• NPC daily activities
• realistic behavior generation
• monotonous repetition
• human activity patterns
• digital immersion

Innovation

• Transformer-CVAE
• contrastive learning
• NPC activity generation
• realistic daily routines
• generative modeling