Intrinsic Motivation

Follow this topic Ask about this topic

Latest papers 35

4 papers in the last four weeks, down 20% on the four weeks before. 0.0% of all new papers.

All topics

Telogenesis: Goal Is All U Need
Mar 10, 2026Zhuoran Deng, Yizhi Zhang, Ziyi Zhang +1Attention Mechanisms Active Perception
Independent Research
Artificial Agency Program: Curiosity, compression, and communication in agents
Feb 27, 2026Richard CsakyAgentic AI Embodied AI
Subjective functions
Dec 17, 2025Samuel J. GershmanIntrinsic Motivation
Department of Psychology and Center for Brain Science · Kempner Institute for the Study of Natural and Artificial Intelligence · Harvard University
ELEMENT: Episodic and Lifelong Exploration via Maximum Entropy
Dec 5, 2024Hongming Li, Zhao Yang, Xiaoxuan Liang +2Intrinsic Reward Methods Reinforcement Learning
Zhejiang Lab, Huangzhou, China · Vrije Universiteit Amsterdam, Amsterdam, the Netherlands · Computational NeuroEngineering Laboratory at the University of Florida, Gainesville, USA
Diversity-Enriched Option-Critic
Nov 4, 2020Anand Kamat, Doina PrecupHierarchical RL Intrinsic Motivation
McGill University · Mila · 3Google deepmind

Mar 10, 2026J/K move · Enter open · S save

Telogenesis: Goal Is All U Need

Zhuoran Deng, Yizhi Zhang, Ziyi Zhang, Wan Shen

Independent Research

Attention Mechanisms Active Perception Intrinsic Motivation Exploration-Exploitation Tradeoff

Open paper AskPDF arXiv

Goal-conditioned systems assume goals are provided externally. We ask whether attentional priorities can emerge endogenously from an agent's internal cognitive state. We propose a priority function that generates observation targets from three epistemic gaps: ignorance (posterior variance), surprise (prediction error), and staleness (temporal decay of confidence in unobserved variables). We validate this in two systems: a minimal attention-allocation environment (2,000 runs) and a modular, partially observable world (500 runs). Ablation shows each component is necessary. A key finding is metric-dependent reversal: under global prediction error, coverage-based rotation wins; under change detection latency, priority-guided allocation wins, with advantage growing monotonically with dimensionality (d = -0.95 at N=48, p < 10^-6). Detection latency follows a power law in attention budget, with a steeper exponent for priority-guided allocation (0.55 vs. 0.40). When the decay rate is made learnable per variable, the system spontaneously recovers environmental volatility structure without supervision (t = 22.5, p < 10^-6). We demonstrate that epistemic gaps alone, without external reward, suffice to generate adaptive priorities that outperform fixed strategies and recover latent environmental structure.

Latest papers 35

Telogenesis: Goal Is All U Need

Artificial Agency Program: Curiosity, compression, and communication in agents

Subjective functions

ELEMENT: Episodic and Lifelong Exploration via Maximum Entropy

Diversity-Enriched Option-Critic