Predictive Representations: Building Blocks Of Intelligence

Abstract

Adaptive behavior often requires predicting future events. The theory of reinforcement learning prescribes what kinds of predictive representations are useful and how to compute them. This paper integrates these theoretical ideas with work on cognition and neuroscience. We pay special attention to the successor representation (SR) and its generalizations, which have been widely applied both as engineering tools and models of brain function. This convergence suggests that particular kinds of predictive representations may function as versatile building blocks of intelligence.

Stats

• citations11
• S2 citations—
• github stars0
• HF likes0
• heat score8.09
• arxiv keycarvalho2024predictive

Related papers

• Data-efficient Reinforcement Learning With Self-predictive Representations (2020)0.00
• Understanding Self-predictive Learning For Reinforcement Learning (2022)0.00
• A First-occupancy Representation For Reinforcement Learning (2021)0.00
• When Is A Prediction Knowledge? (2019)0.00
• Successor Features Combine Elements Of Model-free And Model-based Reinforcement Learning (2019)0.00
• A Neurally Plausible Model Learns Successor Representations In Partially Observable Environments (2019)0.00
• Bridging State And History Representations: Understanding Self-predictive RL (2024)0.00
• Embedded Universal Predictive Intelligence: A Coherent Framework For Multi-agent Learning (2025)0.00