paper-with-me

홈 › Papers

Quality Diversity Through Surprise

2018-07-06 · Daniele Gravina, Antonios Liapis, Georgios N. Yannakakis

Quality diversity is a recent family of evolutionary search algorithms which focus on finding several well-performing (quality) yet different (diversity) solutions with the aim to maintain an appropriate balance between divergence and convergence during search. While quality diversity has already delivered promising results in complex problems, the capacity of divergent search variants for quality diversity remains largely unexplored. Inspired by the notion of surprise as an effective driver of divergent search and its orthogonal nature to novelty this paper investigates the impact of the former to quality diversity performance. For that purpose we introduce three new quality diversity algorithms which employ surprise as a diversity measure, either on its own or combined with novelty, and compare their performance against novelty search with local competition, the state of the art quality diversity algorithm. The algorithms are tested in a robot navigation task across 60 highly deceptive mazes. Our findings suggest that allowing surprise and novelty to operate synergistically for divergence and in combination with local competition leads to quality diversity algorithms of significantly higher efficiency, speed and robustness.

📄 PDF Abstract BibTeX arXiv:1807.02397

Code (1)

https://gitlab.com/2factor/QDSurprise 공식 구현

Tasks

DiversityRobot Navigation

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

SuS: Strategy-aware Surprise for Intrinsic Exploration

2026-01-15 · Mark Kashirskiy, Ilya Makarov arxiv

We propose Strategy-aware Surprise (SuS), a novel intrinsic motivation framework that uses pre-post prediction mismatch as a novelty signal for exploration in reinforcement learning. Unlike traditional curiosity-driven m…

Reinforcement LearningMathematical Reasoning

Geographic Diversity Beats Data Volume for Cross-Domain Generalization in Zero-Label JEPA Driving World Models

2026-07-05 · Santosh Jaiswal arxiv

Self-supervised latent world models can assign a surprise score to driving scenarios without any human labels. A natural follow-up question is whether such a model, trained on driving data from one geographic region, can…

Domain Generalization

Surprise Search for Evolutionary Divergence

2017-06-08 · Daniele Gravina, Antonios Liapis, Georgios N. Yannakakis

Inspired by the notion of surprise for unconventional discovery we introduce a general search algorithm we name surprise search as a new method of evolutionary divergent search. Surprise search is grounded in the diverge…

Evaluating Creative Short Story Generation in Humans and Large Language Models

2024-11-04 · Mete Ismayilzada, Claire Stevenson, Lonneke van der Plas

Story-writing is a fundamental aspect of human imagination, relying heavily on creativity to produce narratives that are novel, effective, and surprising. While large language models (LLMs) have demonstrated the ability …

DiversitySentenceStory Generation

Beyond Surprise: Improving Exploration Through Surprise Novelty

2023-08-09 · Hung Le, Kien Do, Dung Nguyen, Svetha Venkatesh

We present a new computing model for intrinsic rewards in reinforcement learning that addresses the limitations of existing surprise-driven explorations. The reward is the novelty of the surprise rather than the surprise…

Atari GamesRetrieval