Intrinsic Motivation Driven Intuitive Physics Learning Using Deep Reinforcement Learning With Intrinsic Reward Normalization

Abstract

At an early age, human infants are able to learn and build a model of the world very quickly by constantly observing and interacting with objects around them. One of the most fundamental intuitions human infants acquire is intuitive physics. Human infants learn and develop these models, which later serve as prior knowledge for further learning. Inspired by such behaviors exhibited by human infants, we introduce a graphical physics network integrated with deep reinforcement learning. Specifically, we introduce an intrinsic reward normalization method that allows our agent to efficiently choose actions that can improve its intuitive physics model the most. Using a 3D physics engine, we show that our graphical physics network is able to infer object's positions and velocities very effectively, and our deep reinforcement learning network encourages an agent to improve its model by making it continuously interact with objects only using intrinsic motivation. We experiment our model in bot

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keychoi2019intrinsic

Related papers

• Prend: Enhancing Intrinsic Motivation In Reinforcement Learning Through Pre-trained Network Distillation (2024)0.00
• Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction And Intrinsic Motivation (2016)0.00
• From Kicking To Causality: Simulating Infant Agency Detection With A Robust Intrinsic Reward (2025)0.00
• Lucy-skg: Learning To Play Rocket League Efficiently Using Deep Reinforcement Learning (2023)0.00
• Intrinsic Motivation In Model-based Reinforcement Learning: A Brief Review (2023)0.00
• Real-time Model Calibration With Deep Reinforcement Learning (2020)13.74
• Accelerating Reinforcement Learning Agent With Eeg-based Implicit Human Feedback (2020)0.00
• Reward Learning From Human Preferences And Demonstrations In Atari (2018)0.00