IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks

Lee, Youngwoon; Hu, Edward S.; Yang, Zhengyu; Yin, Alex; Lim, Joseph J.

doi:10.48550/arxiv.1911.07246

Cited by 11 publications

(16 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The agent controls the velocity of the end effector and gripper, and the arm is restricted to move in a 2D plane perpendicular to the table's surface. Lastly, we use an IKEA furniture assembly environment from [42]. An agent controls the velocity of a cursor that can lift and place 3 shelves onto a pole.…”

Section: Methodsmentioning

confidence: 99%

DisCo RL: Distribution-Conditioned Reinforcement Learning for General-Purpose Policies

Nasiriany¹,

Pong²,

Nair³

et al. 2021

Preprint

View full text Add to dashboard Cite

Can we use reinforcement learning to learn general-purpose policies that can perform a wide range of different tasks, resulting in flexible and reusable skills? Contextual policies provide this capability in principle, but the representation of the context determines the degree of generalization and expressivity. Categorical contexts preclude generalization to entirely new tasks. Goal-conditioned policies may enable some generalization, but cannot capture all tasks that might be desired. In this paper, we propose goal distributions as a general and broadly applicable task representation suitable for contextual policies. Goal distributions are general in the sense that they can represent any state-based reward function when equipped with an appropriate distribution class, while the particular choice of distribution class allows us to trade off expressivity and learnability. We develop an off-policy algorithm called distribution-conditioned reinforcement learning (DisCo RL) to efficiently learn these policies. We evaluate DisCo RL on a variety of robot manipulation tasks and find that it significantly outperforms prior methods on tasks that require generalization to new goal distributions.

show abstract

Section: Methodsmentioning

confidence: 99%

DisCo RL: Distribution-Conditioned Reinforcement Learning for General-Purpose Policies

Nasiriany¹,

Pong²,

Nair³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Simulators for machine learning. Platforms for simulating realistic environments for model training fall into two broad categories: those built on top of pre-existing game engines (Kolve et al, 2017;Lee et al, 2019;Gan et al, 2020;, and those built from scratch using open-source 3D graphics and physics libraries (Savva et al, 2017;Xia et al, 2018;Xiang et al, 2020;Zeng et al, 2020). While improving simulator performance has been a focus of this line of work, it has been evaluated in a narrow sense (i.e.…”

Section: Related Workmentioning

confidence: 99%

Large Batch Simulation for Deep Reinforcement Learning

Shacklett¹,

Wijmans²,

Petrenko³

et al. 2021

Preprint

View full text Add to dashboard Cite

We accelerate deep reinforcement learning-based training in visually complex 3D environments by two orders of magnitude over prior work, realizing end-to-end training speeds of over 19,000 frames of experience per second on a single GPU and up to 72,000 frames per second on a single eight-GPU machine. The key idea of our approach is to design a 3D renderer and embodied navigation simulator around the principle of "batch simulation": accepting and executing large batches of requests simultaneously. Beyond exposing large amounts of work at once, batch simulation allows implementations to amortize in-memory storage of scene assets, rendering work, data loading, and synchronization costs across many simulation requests, dramatically improving the number of simulated agents per GPU and overall simulation throughput. To balance DNN inference and training costs with faster simulation, we also build a computationally efficient policy DNN that maintains high task performance, and modify training algorithms to maintain sample efficiency when training with large mini-batches. By combining batch simulation and DNN performance optimizations, we demonstrate that PointGoal navigation agents can be trained in complex 3D environments on a single GPU in 1.5 days to 97% of the accuracy of agents trained on a prior state-of-the-art system using a 64-GPU cluster over three days. We provide open-source reference implementations of our batch 3D renderer and simulator to facilitate incorporation of these ideas into RL systems.

show abstract

“…The OpenAI Gym (Brockman et al, 2016) includes a set of continuous control domains that have become a popular benchmark in continuous RL (Duan et al, 2016;Henderson et al, 2017). More recent task suites such as Meta-world (Yu et al, 2019), SURREAL (Fan et al, 2018), RLbench (James et al, 2019) and IKEA (Lee et al, 2019), have been published in an attempt to satisfy the demand for tasks suites that facilitate the study of algorithms related to multi-scale control, multitask, transfer, and meta learning. dm_control includes its own sets of control tasks, in three categories:…”

Section: Tasksmentioning

confidence: 99%

dm_control: Software and Tasks for Continuous Control

Tassa,

Tunyasuvunakool,

Muldal

et al. 2020

Preprint

View full text Add to dashboard Cite

The dm_control software package is a collection of Python libraries and task suites for reinforcement learning agents in an articulated-body simulation. A MuJoCo wrapper provides convenient bindings to functions and data structures. The PyMJCF and Composer libraries enable procedural model manipulation and task authoring. The Control Suite is a fixed set of tasks with standardised structure, intended to serve as performance benchmarks. The Locomotion framework provides high-level abstractions and examples of locomotion tasks. A set of configurable manipulation tasks with a robot arm and snap-together bricks is also included.

show abstract

IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks

Cited by 11 publications

References 0 publications

DisCo RL: Distribution-Conditioned Reinforcement Learning for General-Purpose Policies

DisCo RL: Distribution-Conditioned Reinforcement Learning for General-Purpose Policies

Large Batch Simulation for Deep Reinforcement Learning

dm_control: Software and Tasks for Continuous Control

Contact Info

Product

Resources

About