Infants are experts at playing, with an amazing ability to generate novel structured behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to replicate some of these abilities with a neural network that implements curiosity-driven intrinsic motivation. Using a simple but ecologically naturalistic simulated environment in which the agent can move and interact with objects it sees, the agent learns a world model predicting the dynamic consequences of its actions. Simultaneously, the agent learns to take actions that adversarially challenge the developing world model, pushing the agent to explore novel and informative interactions with its environment. We demonstrate that this policy leads to the self-supervised emergence of a spectrum of complex behaviors, including ego motion prediction, object attention, and object gathering. Moreover, the world model that the agent learns supports improved performance on object dynamics prediction and localization tasks. Our results are a proof-of-principle that computational models of intrinsic motivation might account for key features of developmental visuomotor learning in infants.
Intrinsic Motivation and Episodic Memories for Robot Exploration of High-Dimensional Sensory Spaces
The BioRobotics Institute, Scuola Superiore Sant'Anna(圣安娜高等学校生物机器人研究所);Scuola Superiore Sant'Anna(圣安娜高等学校);Sony Computer Science Laboratories(索尼计算机科学实验室)
Curiosity in exploring chemical space: Intrinsic rewards for deep molecular reinforcement learning
University of Göttingen(哥廷根大学);University of Toronto(多伦多大学);Vector Institute for Artificial Intelligence(向量人工智能研究所);Canadian Institute for Advanced Research(加拿大高等研究院)
Wonder Wins Ways: Curiosity-Driven Exploration through Multi-Agent Contextual Calibration
Shanghai Jiao Tong University(上海交通大学);School of Automation and Intelligent Sensing(自动化与智能感知学院);Key Laboratory of System Control and Information Processing(系统控制与信息处理重点实验室);Ministry of Education of China(中华人民共和国教育部);National Key Laboratory of Human-Machine Hybrid Augmented Intelligence(人机混合增强智能国家级重点实验室);Institute of Artificial Intelligence and Robotics(人工智能与机器人研究院)
Towards Empowerment Gain through Causal Structure Learning in Model-Based RL
National Key Laboratory for Novel Software Technology, Nanjing University(南京大学计算机软件新技术国家重点实验室);University of California, San Diego(加利福尼亚大学圣迭戈分校);MBZUAI(Mohamed bin Zayed 人工智能大学);University of Liverpool(利物浦大学);School of Intelligence Science and Technology, Nanjing University(南京大学智能科学与技术学院)