Intrinsic Motivation Driven Intuitive Physics Learning using Deep Reinforcement Learning with Intrinsic Reward Normalization

2019-07-06 · JaeWon Choi, Sung-Eui Yoon

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 both stationary and non-stationary state problems and show benefits of our approach in terms of the number of different actions the agent performs and the accuracy of agent's intuition model. Videos are at https://www.youtube.com/watch?v=pDbByp91r3M&t=2s

📄 PDF Abstract BibTeX arXiv:1907.03116

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Measuring and Modeling Physical Intrinsic Motivation

2023-05-22 · Julio Martinez, Felix Binder, Haoliang Wang, Nick Haber 외

Humans are interactive agents driven to seek out situations with interesting physical dynamics. Here we formalize the functional form of physical intrinsic motivation. We first collect ratings of how interesting humans f…

Prediction

Curiosity-driven Exploration in Sparse-reward Multi-agent Reinforcement Learning

2023-02-21 · Jiong Li, Pratik Gajane

Sparsity of rewards while applying a deep reinforcement learning method negatively affects its sample-efficiency. A viable solution to deal with the sparsity of rewards is to learn via intrinsic motivation which advocate…

Deep Reinforcement Learning Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning+1

Noisy Agents: Self-supervised Exploration by Predicting Auditory Events

2020-07-27 · Chuang Gan, Xiaoyu Chen, Phillip Isola, Antonio Torralba 외

Humans integrate multiple sensory modalities (e.g. visual and audio) to build a causal understanding of the physical world. In this work, we propose a novel type of intrinsic motivation for Reinforcement Learning (RL) th…

Atari Games Reinforcement Learning (RL)

PhysQ: A Physics Informed Reinforcement Learning Framework for Building Control

2022-11-21 · Gargya Gokhale, Bert Claessens, Chris Develder

Large-scale integration of intermittent renewable energy sources calls for substantial demand side flexibility. Given that the built environment accounts for approximately 40% of total energy consumption in EU, unlocking…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Expanding the Active Inference Landscape: More Intrinsic Motivations in the Perception-Action Loop

2018-06-21 · Martin Biehl, Christian Guckelsberger, Christoph Salge, Simón C. Smith 외

Active inference is an ambitious theory that treats perception, inference and action selection of autonomous agents under the heading of a single principle. It suggests biologically plausible explanations for many cognit…

Reinforcement Learning