paper-with-me

Papers

Active Domain Randomization

2019-04-09 · Bhairav Mehta, Manfred Diaz, Florian Golemo, Christopher J. Pal, Liam Paull

Domain randomization is a popular technique for improving domain transfer, often used in a zero-shot setting when the target domain is unknown or cannot easily be used for training. In this work, we empirically examine the effects of domain randomization on agent generalization. Our experiments show that domain randomization may lead to suboptimal, high-variance policies, which we attribute to the uniform sampling of environment parameters. We propose Active Domain Randomization, a novel algorithm that learns a parameter sampling strategy. Our method looks for the most informative environment variations within the given randomization ranges by leveraging the discrepancies of policy rollouts in randomized and reference environment instances. We find that training more frequently on these instances leads to better overall agent generalization. Our experiments across various physics-based simulated and real-robot tasks show that this enhancement leads to more robust, consistent policies.

📄 PDF Abstract BibTeX arXiv:1904.04762

Code (2)

montrealrobotics/active-domainrand 공식 구현 pytorch
lesleychou/adr_mahimahi pytorch

Tasks

Attribute

Similar Papers 제목 키워드 기반

BayRnTune: Adaptive Bayesian Domain Randomization via Strategic Fine-tuning

2023-10-16 · Tianle Huang, Nitish Sontakke, K. Niranjan Kumar, Irfan Essa 외

Domain randomization (DR), which entails training a policy with randomized dynamics, has proven to be a simple yet effective algorithm for reducing the gap between simulation and the real world. However, DR often require…

Domain Randomization for Active Pose Estimation

2019-03-10 · Xinyi Ren, Jianlan Luo, Eugen Solowjow, Juan Aparicio Ojea 외

Accurate state estimation is a fundamental component of robotic control. In robotic manipulation tasks, as is our focus in this work, state estimation is essential for identifying the positions of objects in the scene, f…

Pose EstimationState Estimation

Generating Automatic Curricula via Self-Supervised Active Domain Randomization

2020-02-18 · Sharath Chandra Raparthy, Bhairav Mehta, Florian Golemo, Liam Paull

Goal-directed Reinforcement Learning (RL) traditionally considers an agent interacting with an environment, prescribing a real-valued reward to an agent proportional to the completion of some goal. Goal-directed RL has s…

Reinforcement LearningReinforcement Learning (RL)

Learning Domain Randomization Distributions for Training Robust Locomotion Policies

2019-06-02 · Melissa Mozifian, Juan Camilo Gamboa Higuera, David Meger, Gregory Dudek

Domain randomization (DR) is a successful technique for learning robust policies for robot systems, when the dynamics of the target robot system are unknown. The success of policies trained with domain randomization howe…

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-learningReinforcement LearningReinforcement Learning (RL)