Environment Exploration
Environment exploration in robotics and AI focuses on enabling agents to efficiently and effectively learn about and navigate unknown environments, optimizing for factors like map creation, sensor fusion, and efficient decision-making. Current research emphasizes leveraging deep learning models, such as neural networks and transformers, for tasks like map prediction, sensor calibration (e.g., LiDAR-camera), and skill acquisition, often incorporating techniques like reinforcement learning and information gain calculations to guide exploration strategies. These advancements have implications for various fields, including autonomous navigation, game design, and personalized healthcare, by improving the robustness and adaptability of AI agents in complex and dynamic settings.
Papers
Accelerating exploration and representation learning with offline pre-training
Bogdan Mazoure, Jake Bruce, Doina Precup, Rob Fergus, Ankit Anand
CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
Guohao Li, Hasan Abed Al Kader Hammoud, Hani Itani, Dmitrii Khizbullin, Bernard Ghanem
Finding Things in the Unknown: Semantic Object-Centric Exploration with an MAV
Sotiris Papatheodorou, Nils Funk, Dimos Tzoumanikas, Christopher Choi, Binbin Xu, Stefan Leutenegger
Learning Sparse Control Tasks from Pixels by Latent Nearest-Neighbor-Guided Explorations
Ruihan Zhao, Ufuk Topcu, Sandeep Chinchali, Mariano Phielipp
Mitigating Adversarial Attacks in Deepfake Detection: An Exploration of Perturbation and AI Techniques
Saminder Dhesi, Laura Fontes, Pedro Machado, Isibor Kennedy Ihianle, Farhad Fassihi Tash, David Ada Adama
Self-supervised network distillation: an effective approach to exploration in sparse reward environments
Matej Pecháč, Michal Chovanec, Igor Farkaš
Learning How to Infer Partial MDPs for In-Context Adaptation and Exploration
Chentian Jiang, Nan Rosemary Ke, Hado van Hasselt
Investigating the role of model-based learning in exploration and transfer
Jacob Walker, Eszter Vértes, Yazhe Li, Gabriel Dulac-Arnold, Ankesh Anand, Théophane Weber, Jessica B. Hamrick
Exploitation and exploration in text evolution. Quantifying planning and translation flows during writing
Donald Ruggiero Lo Sardo, Pietro Gravino, Christine Cuskley, Vittorio Loreto
Look around and learn: self-improving object detection by exploration
Gianluca Scarpellini, Stefano Rosa, Pietro Morerio, Lorenzo Natale, Alessio Del Bue