Universal AI maximizes Variational Empowerment
This paper presents a theoretical framework unifying AIXI -- a model of universal AI -- with variational empowerment as an intrinsic drive for exploration. We build on the existing framework of Self-AIXI -- a universal learning agent that predicts its own actions -- by showing how one of its established terms can be interpreted as a variational empowerment objective. We further demonstrate that universal AI's planning process can be cast as minimizing expected variational free energy (the core principle of active Inference), thereby revealing how universal AI agents inherently balance goal-directed behavior with uncertainty reduction curiosity). Moreover, we argue that power-seeking tendencies of universal AI agents can be explained not only as an instrumental strategy to secure future reward, but also as a direct consequence of empowerment maximization -- i.e.\ the agent's intrinsic drive to maintain or expand its own controllability in uncertain environments. Our main contribution is to show how these intrinsic motivations (empowerment, curiosity) systematically lead universal AI agents to seek and sustain high-optionality states. We prove that Self-AIXI asymptotically converges to the same performance as AIXI under suitable conditions, and highlight that its power-seeking behavior emerges naturally from both reward maximization and curiosity-driven exploration. Since AIXI can be view as a Bayes-optimal mathematical formulation for Artificial General Intelligence (AGI), our result can be useful for further discussion on AI safety and the controllability of AGI.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
IR-VIC: Unsupervised Discovery of Sub-goals for Transfer in RL
We propose a novel framework to identify sub-goals useful for exploration in sequential decision making tasks under partial observability. We utilize the variational intrinsic control framework (Gregor et.al., 2016) whic…
Decision MakingHierarchical Reinforcement LearningSequential Decision MakingEmpowerment Gain and Causal Model Construction: Children and adults are sensitive to controllability and variability in their causal interventions
Learning about the causal structure of the world is a fundamental problem for human cognition. Causal models and especially causal learning have proved to be difficult for large pretrained models using standard technique…
Reinforcement LearningExperimental Evidence that Empowerment May Drive Exploration in Sparse-Reward Environments
Reinforcement Learning (RL) is known to be often unsuccessful in environments with sparse extrinsic rewards. A possible countermeasure is to endow RL agents with an intrinsic reward function, or 'intrinsic motivation', w…
Reinforcement Learning (RL)Learning to Perceive the World Through Control: Empowerment-Based Representation Learning
In many practical reinforcement learning environments, observations are far higher-dimensional than the variables that matter for control. In this work, we ask: can we learn representations that capture only control-rele…
Representation LearningReinforcement LearningHierarchical Empowerment: Towards Tractable Empowerment-Based Skill Learning
General purpose agents will require large repertoires of skills. Empowerment -- the maximum mutual information between skills and states -- provides a pathway for learning large collections of distinct skills, but mutual…
Hierarchical Reinforcement Learning