Autotelic Reinforcement Learning: Exploring Intrinsic Motivations For Skill Acquisition In Open-ended Environments

Abstract

This paper presents a comprehensive overview of autotelic Reinforcement Learning (RL), emphasizing the role of intrinsic motivations in the open-ended formation of skill repertoires. We delineate the distinctions between knowledge-based and competence-based intrinsic motivations, illustrating how these concepts inform the development of autonomous agents capable of generating and pursuing self-defined goals. The typology of Intrinsically Motivated Goal Exploration Processes (IMGEPs) is explored, with a focus on the implications for multi-goal RL and developmental robotics. The autotelic learning problem is framed within a reward-free Markov Decision Process (MDP), WHERE agents must autonomously represent, generate, and master their own goals. We address the unique challenges in evaluating such agents, proposing various metrics for measuring exploration, generalization, and robustness in complex environments. This work aims to advance the understanding of autotelic RL agents and their p

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keysrivastava2025autotelic

Related papers

• Autotelic Agents With Intrinsically Motivated Goal-conditioned Reinforcement Learning: A Short Survey (2020)0.00
• Autotelic Reinforcement Learning In Multi-agent Environments (2022)0.00
• An Information-theoretic Perspective On Intrinsic Motivation In Reinforcement Learning: A Survey (2022)11.93
• Intrinsic Motivation In Model-based Reinforcement Learning: A Brief Review (2023)0.00
• A Survey On Intrinsic Motivation In Reinforcement Learning (2019)0.00
• Learning With Amigo: Adversarially Motivated Intrinsic Goals (2020)0.00
• Rlexplore: Accelerating Research In Intrinsically-motivated Reinforcement Learning (2024)5.33
• A Unified Strategy For Implementing Curiosity And Empowerment Driven Reinforcement Learning (2018)0.00