paper-with-me

Papers

Benchmarking Domain Randomisation for Visual Sim-to-Real Transfer

2020-11-13 · Raghad Alghonaim, Edward Johns

Domain randomisation is a very popular method for visual sim-to-real transfer in robotics, due to its simplicity and ability to achieve transfer without any real-world images at all. Nonetheless, a number of design choices must be made to achieve optimal transfer. In this paper, we perform a comprehensive benchmarking study on these different choices, with two key experiments evaluated on a real-world object pose estimation task. First, we study the rendering quality, and find that a small number of high-quality images is superior to a large number of low-quality images. Second, we study the type of randomisation, and find that both distractors and textures are important for generalisation to novel environments.

📄 PDF Abstract BibTeX arXiv:2011.07112

Code (0)

등록된 구현이 없습니다.

Tasks

BenchmarkingPose Estimation

Similar Papers 제목 키워드 기반

BehAVE: Behaviour Alignment of Video Game Encodings

2024-02-02 · Nemanja Rašajski, Chintan Trivedi, Konstantinos Makantasis, Antonios Liapis 외

Domain randomisation enhances the transferability of vision models across visually distinct domains with similar content. However, current methods heavily depend on intricate simulation engines, hampering feasibility and…

DiversityFPS GamesVideo Understanding

Analysing Deep Reinforcement Learning Agents Trained with Domain Randomisation

2019-12-18 · Tianhong Dai, Kai Arulkumaran, Tamara Gerbert, Samyakh Tukra 외

Deep reinforcement learning has the potential to train robots to perform complex tasks in the real world without requiring accurate models of the robot or its environment. A practical approach is to train agents in simul…

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

TWIST: Teacher-Student World Model Distillation for Efficient Sim-to-Real Transfer

2023-11-07 · Jun Yamada, Marc Rigter, Jack Collins, Ingmar Posner

Model-based RL is a promising approach for real-world robotics due to its improved sample efficiency and generalization capabilities compared to model-free RL. However, effective model-based RL solutions for vision-based…

CALF: Communication-Aware Learning Framework for Distributed Reinforcement Learning

2026-03-13 · Carlos Purves, Pietro Lio' arxiv

Distributed reinforcement learning policies face network delays, jitter, and packet loss when deployed across edge devices and cloud servers. Standard RL training assumes zero-latency interaction, causing severe performa…

Reinforcement Learning

Attention-Privileged Reinforcement Learning

2019-11-19 · Sasha Salter, Dushyant Rao, Markus Wulfmeier, Raia Hadsell 외

Image-based Reinforcement Learning is known to suffer from poor sample efficiency and generalisation to unseen visuals such as distractors (task-independent aspects of the observation space). Visual domain randomisation …

reinforcement-learningReinforcement LearningReinforcement Learning (RL)