Prototyping Three Key Properties Of Specific Curiosity In Computational Reinforcement Learning

Abstract

Curiosity for machine agents has been a focus of intense research. The study of human and animal curiosity, particularly specific curiosity, has unearthed several properties that would offer important benefits for machine learners, but that have not yet been well-explored in machine intelligence. In this work, we introduce three of the most immediate of these properties -- directedness, cessation when satisfied, and voluntary exposure -- and show how they may be implemented together in a proof-of-concept reinforcement learning agent; further, we demonstrate how the properties manifest in the behaviour of this agent in a simple non-episodic grid-world environment that includes curiosity-inducing locations and induced targets of curiosity. As we would hope, the agent exhibits short-term directed behaviour while updating long-term preferences to adaptively seek out curiosity-inducing situations. This work therefore presents a novel view into how specific curiosity operates and in the futu

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyady2022prototyping

Related papers

• Five Properties Of Specific Curiosity You Didn't Know Curious Machines Should Have (2022)0.00
• From Psychological Curiosity To Artificial Curiosity: Curiosity-driven Learning In Artificial Intelligence Tasks (2022)0.00
• Is Curiosity All You Need? On The Utility Of Emergent Behaviours From Curious Exploration (2021)0.00
• Wonder Wins Ways: Curiosity-driven Exploration Through Multi-agent Contextual Calibration (2025)0.00
• Dynamic Memory-based Curiosity: A Bootstrap Approach For Exploration (2022)0.00
• Curiosity-driven Multi-agent Exploration With Mixed Objectives (2022)0.00
• A Unified Strategy For Implementing Curiosity And Empowerment Driven Reinforcement Learning (2018)0.00
• Curiosity-driven Exploration Via Latent Bayesian Surprise (2021)0.00