Robogen: Towards unleashing infinite data for automated robot learning via generative simulation
We present RoboGen, a generative robotic agent that automatically learns diverse robotic
skills at scale via generative simulation. RoboGen leverages the latest advancements in …
skills at scale via generative simulation. RoboGen leverages the latest advancements in …
Moto: Offline pre-training to online fine-tuning for model-based robot learning
R Rafailov, KB Hatch, V Kolev… - … on Robot Learning, 2023 - proceedings.mlr.press
We study the problem of offline pre-training and online fine-tuning for reinforcement learning
from high-dimensional observations in the context of realistic robot tasks. Recent offline …
from high-dimensional observations in the context of realistic robot tasks. Recent offline …
Gen2sim: Scaling up robot learning in simulation with generative models
Generalist robot manipulators need to learn a wide variety of manipulation skills across
diverse environments. Current robot training pipelines rely on humans to provide kinesthetic …
diverse environments. Current robot training pipelines rely on humans to provide kinesthetic …
Mimicgen: A data generation system for scalable robot learning using human demonstrations
Imitation learning from a large set of human demonstrations has proved to be an effective
paradigm for building capable robot agents. However, the demonstrations can be extremely …
paradigm for building capable robot agents. However, the demonstrations can be extremely …
Pre-training for robots: Offline rl enables learning new tasks from a handful of trials
Progress in deep learning highlights the tremendous potential of utilizing diverse robotic
datasets for attaining effective generalization and makes it enticing to consider leveraging …
datasets for attaining effective generalization and makes it enticing to consider leveraging …
Bridge data: Boosting generalization of robotic skills with cross-domain datasets
Robot learning holds the promise of learning policies that generalize broadly. However,
such generalization requires sufficiently diverse datasets of the task of interest, which can be …
such generalization requires sufficiently diverse datasets of the task of interest, which can be …
Generalization with lossy affordances: Leveraging broad offline data for learning visuomotor tasks
The use of broad datasets has proven to be crucial for generalization for a wide range of
fields. However, how to effectively make use of diverse multi-task data for novel downstream …
fields. However, how to effectively make use of diverse multi-task data for novel downstream …
Scaling robot learning with semantically imagined experience
Recent advances in robot learning have shown promise in enabling robots to perform a
variety of manipulation tasks and generalize to novel scenarios. One of the key contributing …
variety of manipulation tasks and generalize to novel scenarios. One of the key contributing …
Learning to generalize across long-horizon tasks from human demonstrations
Imitation learning is an effective and safe technique to train robot policies in the real world
because it does not depend on an expensive random exploration process. However, due to …
because it does not depend on an expensive random exploration process. However, due to …
robosuite: A modular simulation framework and benchmark for robot learning
robosuite is a simulation framework for robot learning powered by the MuJoCo physics
engine. It offers a modular design for creating robotic tasks as well as a suite of benchmark …
engine. It offers a modular design for creating robotic tasks as well as a suite of benchmark …