Robust Visual Domain Randomization for Reinforcement Learning

2019-10-23 · Reda Bahi Slaoui, William R. Clements, Jakob N. Foerster, Sébastien Toth

Producing agents that can generalize to a wide range of visually different environments is a significant challenge in reinforcement learning. One method for overcoming this issue is visual domain randomization, whereby at the start of each training episode some visual aspects of the environment are randomized so that the agent is exposed to many possible variations. However, domain randomization is highly inefficient and may lead to policies with high variance across domains. Instead, we propose a regularization method whereby the agent is only trained on one variation of the environment, and its learned state representations are regularized during training to be invariant across domains. We conduct experiments that demonstrate that our technique leads to more efficient and robust learning than standard domain randomization, while achieving equal generalization scores.

📄 PDF Abstract BibTeX arXiv:1910.10537

Code (2)

IndustAI/visual-domain-randomization 공식 구현

uncharted-technologies/robust-domain-randomization 공식 구현

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Pre-training of Deep RL Agents for Improved Learning under Domain Randomization

2021-04-29 · Artemij Amiranashvili, Max Argus, Lukas Hermann, Wolfram Burgard 외

Visual domain randomization in simulated environments is a widely used method to transfer policies trained in simulation to real robots. However, domain randomization and augmentation hamper the training of a policy. As …

reinforcement-learning Reinforcement Learning (RL)

Robust Domain Randomization for Reinforcement Learning

2019-09-25 · Reda Bahi Slaoui, William R. Clements, Jakob N. Foerster, Sébastien Toth

Producing agents that can generalize to a wide range of environments is a significant challenge in reinforcement learning. One method for overcoming this issue is domain randomization, whereby at the start of each traini…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Real2Sim or Sim2Real: Robotics Visual Insertion using Deep Reinforcement Learning and Real2Sim Policy Adaptation

2022-06-06 · YiWen Chen, Xue Li, Sheng Guo, Xian Yao Ng 외

Reinforcement learning has shown a wide usage in robotics tasks, such as insertion and grasping. However, without a practical sim2real strategy, the policy trained in simulation could fail on the real task. There are als…

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

BayesSimIG: Scalable Parameter Inference for Adaptive Domain Randomization with IsaacGym

2021-07-09 · Rika Antonova, Fabio Ramos, Rafael Possas, Dieter Fox

BayesSim is a statistical technique for domain randomization in reinforcement learning based on likelihood-free inference of simulation parameters. This paper outlines BayesSimIG: a library that provides an implementatio…

GPU Reinforcement Learning (RL)

DROPO: Sim-to-Real Transfer with Offline Domain Randomization

2022-01-20 · Gabriele Tiboni, Karol Arndt, Ville Kyrki

In recent years, domain randomization over dynamics parameters has gained a lot of traction as a method for sim-to-real transfer of reinforcement learning policies in robotic manipulation; however, finding optimal random…

Reinforcement Learning (RL)