paper-with-me

홈 › Papers

Dropout's Dream Land: Generalization from Learned Simulators to Reality

2021-09-17 · Zac Wellmer, James T. Kwok

A World Model is a generative model used to simulate an environment. World Models have proven capable of learning spatial and temporal representations of Reinforcement Learning environments. In some cases, a World Model offers an agent the opportunity to learn entirely inside of its own dream environment. In this work we explore improving the generalization capabilities from dream environments to real environments (Dream2Real). We present a general approach to improve a controller's ability to transfer from a neural network dream environment to reality at little additional cost. These improvements are gained by drawing on inspiration from Domain Randomization, where the basic idea is to randomize as much of a simulator as possible without fundamentally changing the task at hand. Generally, Domain Randomization assumes access to a pre-built simulator with configurable parameters but oftentimes this is not available. By training the World Model using dropout, the dream environment is capable of creating a nearly infinite number of different dream environments. Previous use cases of dropout either do not use dropout at inference time or averages the predictions generated by multiple sampled masks (Monte-Carlo Dropout). Dropout's Dream Land leverages each unique mask to create a diverse set of dream environments. Our experimental results show that Dropout's Dream Land is an effective technique to bridge the reality gap between dream environments and reality. Furthermore, we additionally perform an extensive set of ablation studies.

📄 PDF Abstract BibTeX arXiv:2109.08342

Code (1)

zacwellmer/dropoutsdreamland 공식 구현 tf

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

DayDreamer: World Models for Physical Robot Learning

2022-06-28 · Philipp Wu, Alejandro Escontrela, Danijar Hafner, Ken Goldberg 외

To solve tasks in complex environments, robots need to learn from experience. Deep reinforcement learning is a common approach to robot learning but requires a large amount of trial and error to learn, limiting its deplo…

Deep Reinforcement LearningNavigatereinforcement-learningReinforcement Learning (RL)

DreamHead: Learning Spatial-Temporal Correspondence via Hierarchical Diffusion for Audio-driven Talking Head Synthesis

2024-09-16 · Fa-Ting Hong, Yunfei Liu, Yu Li, Changyin Zhou 외

Audio-driven talking head synthesis strives to generate lifelike video portraits from provided audio. The diffusion model, recognized for its superior quality and robust generalization, has been explored for this task. H…

Talking Head Generation

Dropout in Training Neural Networks: Flatness of Solution and Noise Structure

2021-11-01 · Zhongwang Zhang, Hanxu Zhou, Zhi-Qin John Xu

It is important to understand how the popular regularization method dropout helps the neural network training find a good generalization solution. In this work, we show that the training with dropout finds the neural net…

ManiDreams: An Open-Source Library for Robust Object Manipulation via Uncertainty-aware Task-specific Intuitive Physics

2026-03-18 · Gaotian Wang, Kejia Ren, Andrew S. Morgan, Kaiyu Hang arxiv

Dynamics models, whether simulators or learned world models, have long been central to robotic manipulation, but most focus on minimizing prediction error rather than confronting a more fundamental challenge: real-world …

Learned Simulators for Turbulence

2021-09-29 · ICLR 2022 4 · Kim Stachenfeld, Drummond Buschman Fielding, Dmitrii Kochkov, Miles Cranmer 외

Turbulence simulation with classical numerical solvers requires very high-resolution grids to accurately resolve dynamics. Here we train learned simulators at low spatial and temporal resolutions to capture turbulent dyn…