Agent-centric learning: from external reward maximization to internal knowledge curation
The pursuit of general intelligence has traditionally centered on external objectives: an agent's control over its environments or mastery of specific tasks. This external focus, however, can produce specialized agents that lack adaptability. We propose representational empowerment, a new perspective towards a truly agent-centric learning paradigm by moving the locus of control inward. This objective measures an agent's ability to controllably maintain and diversify its own knowledge structures. We posit that the capacity -- to shape one's own understanding -- is an element for achieving better ``preparedness'' distinct from direct environmental influence. Focusing on internal representations as the main substrate for computing empowerment offers a new lens through which to design adaptable intelligent systems.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Co-Evolution of Policy and Internal Reward for Language Agents
Large language model (LLM) agents learn by interacting with environments, but long-horizon training remains fundamentally bottlenecked by sparse and delayed rewards. Existing methods typically address this challenge thro…
Reward is not Necessary: How to Create a Modular & Compositional Self-Preserving Agent for Life-Long Learning
Reinforcement Learning views the maximization of rewards and avoidance of punishments as central to explaining goal-directed behavior. However, over a life, organisms will need to learn about many different aspects of th…
Inverse Rational Control: Inferring What You Think from How You Forage
Complex behaviors are often driven by an internal model, which integrates sensory information over time and facilitates long-term planning. Inferring an agent's internal model is a crucial ingredient in social interactio…
Imitation LearningReinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent
Retrieval-augmented generation (RAG) is a common strategy to reduce hallucinations in Large Language Models (LLMs). While reinforcement learning (RL) can enable LLMs to act as search agents by activating retrieval capabi…
RAGReinforcement Learning (RL)RetrievalRetrieval-augmented GenerationA Reinforcement Learning Theory for Homeostatic Regulation
Reinforcement learning models address animal's behavioral adaptation to its changing "external" environment, and are based on the assumption that Pavlovian, habitual and goal-directed responses seek to maximize reward ac…
Learning Theoryreinforcement-learningReinforcement LearningReinforcement Learning (RL)