Learning Efficient Representation For Intrinsic Motivation

Abstract

Mutual Information between agent Actions and environment States (MIAS) quantifies the influence of agent on its environment. Recently, it was found that the maximization of MIAS can be used as an intrinsic motivation for artificial agents. In literature, the term empowerment is used to represent the maximum of MIAS at a certain state. While empowerment has been shown to solve a broad range of reinforcement learning problems, its calculation in arbitrary dynamics is a challenging problem because it relies on the estimation of mutual information. Existing approaches, which rely on sampling, are limited to low dimensional spaces, because high-confidence distribution-free lower bounds for mutual information require exponential number of samples. In this work, we develop a novel approach for the estimation of empowerment in unknown dynamics from visual observation only, without the need to sample for MIAS. The core idea is to represent the relation between action sequences and future states

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhao2019learning

Related papers

• Information Is Power: Intrinsic Control Via Information Capture (2021)0.00
• A Unified Strategy For Implementing Curiosity And Empowerment Driven Reinforcement Learning (2018)0.00
• Emergent Cooperation Through Mutual Information Maximization (2020)0.00
• Experimental Evidence That Empowerment May Drive Exploration In Sparse-reward Environments (2021)0.00
• Mutual Information Tracks Policy Coherence In Reinforcement Learning (2025)0.00
• A Unified Bellman Optimality Principle Combining Reward Maximization And Empowerment (2019)0.00
• Influence-based Reinforcement Learning For Intrinsically-motivated Agents (2021)0.00
• MIR: Efficient Exploration In Episodic Multi-agent Reinforcement Learning Via Mutual Intrinsic Reward (2025)0.00