Arbitrarily Scalable Environment Generators via Neural Cellular Automata

• URL: http://arxiv.org/abs/2310.18622v1
• Date: Sat, 28 Oct 2023 07:30:09 GMT
• Title: Arbitrarily Scalable Environment Generators via Neural Cellular Automata
• Authors: Yulun Zhang, Matthew C. Fontaine, Varun Bhatt, Stefanos Nikolaidis, Jiaoyang Li
• Abstract summary: We show that NCA environment generators maintain consistent, regularized patterns regardless of environment size. Our method scales a single-agent reinforcement learning policy to arbitrarily large environments with similar patterns.
• Score: 55.150593161240444
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study the problem of generating arbitrarily large environments to improve the throughput of multi-robot systems. Prior work proposes Quality Diversity (QD) algorithms as an effective method for optimizing the environments of automated warehouses. However, these approaches optimize only relatively small environments, falling short when it comes to replicating real-world warehouse sizes. The challenge arises from the exponential increase in the search space as the environment size increases. Additionally, the previous methods have only been tested with up to 350 robots in simulations, while practical warehouses could host thousands of robots. In this paper, instead of optimizing environments, we propose to optimize Neural Cellular Automata (NCA) environment generators via QD algorithms. We train a collection of NCA generators with QD algorithms in small environments and then generate arbitrarily large environments from the generators at test time. We show that NCA environment generators maintain consistent, regularized patterns regardless of environment size, significantly enhancing the scalability of multi-robot systems in two different domains with up to 2,350 robots. Additionally, we demonstrate that our method scales a single-agent reinforcement learning policy to arbitrarily large environments with similar patterns. We include the source code at \url{https://github.com/lunjohnzhang/warehouse_env_gen_nca_public}.

Related papers

• Robotic warehousing operations: a learn-then-optimize approach to large-scale neighborhood search [84.39855372157616]
  This paper supports robotic parts-to-picker operations in warehousing by optimizing order-workstation assignments, item-pod assignments and the schedule of order fulfillment at workstations. We solve it via large-scale neighborhood search, with a novel learn-then-optimize approach to subproblem generation. In collaboration with Amazon Robotics, we show that our model and algorithm generate much stronger solutions for practical problems than state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-08-29T20:22:22Z)
• Multi-Objective Optimization Using Adaptive Distributed Reinforcement Learning [8.471466670802815]
  We propose a multi-objective, multi-agent reinforcement learning (MARL) algorithm with high learning efficiency and low computational requirements. We test our algorithm in an ITS environment with edge cloud computing. Our algorithm also addresses various practical concerns with its modularized and asynchronous online training method.
  arXiv  Detail & Related papers  (2024-03-13T18:05:16Z)
• Distributed Inference and Fine-tuning of Large Language Models Over The Internet [91.00270820533272]
  Large language models (LLMs) are useful in many NLP tasks and become more capable with size. These models require high-end hardware, making them inaccessible to most researchers. We develop fault-tolerant inference algorithms and load-balancing protocols that automatically assign devices to maximize the total system throughput.
  arXiv  Detail & Related papers  (2023-12-13T18:52:49Z)
• RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation [68.70755196744533]
  RoboGen is a generative robotic agent that automatically learns diverse robotic skills at scale via generative simulation. Our work attempts to extract the extensive and versatile knowledge embedded in large-scale models and transfer them to the field of robotics.
  arXiv  Detail & Related papers  (2023-11-02T17:59:21Z)
• Multi-Robot Coordination and Layout Design for Automated Warehousing [55.150593161240444]
  We show that, even with state-of-the-art MAPF algorithms, commonly used human-designed layouts can lead to congestion for warehouses with large numbers of robots. We extend existing automatic scenario generation methods to optimize warehouse layouts. Results show that our optimized warehouse layouts (1) reduce traffic congestion and thus improve throughput, (2) improve the scalability of the automated warehouses by doubling the number of robots in some cases, and (3) are capable of generating layouts with user-specified diversity measures.
  arXiv  Detail & Related papers  (2023-05-10T20:00:06Z)
• Scalable Multi-robot Motion Planning for Congested Environments With Topological Guidance [2.846144602096543]
  Multi-robot motion planning (MRMP) is the problem of finding collision-free paths for a set of robots in a continuous state space. We extend an existing single-robot motion planning method to leverage the improved efficiency provided by topological guidance. We demonstrate our method's ability to efficiently plan paths in complex environments with many narrow passages, scaling to robot teams of size up to 25 times larger than existing methods.
  arXiv  Detail & Related papers  (2022-10-13T16:26:01Z)
• Deep Surrogate Assisted Generation of Environments [7.217405582720078]
  Quality diversity (QD) optimization has been proven to be an effective component of environment generation algorithms. We propose Deep Surrogate Assisted Generation of Environments (DSAGE), a sample-efficient QD environment generation algorithm. Results in two benchmark domains show that DSAGE significantly outperforms existing QD environment generation algorithms.
  arXiv  Detail & Related papers  (2022-06-09T00:14:03Z)
• You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient [88.58536093633167]
  Existing model compression approaches require re-compression or fine-tuning across diverse constraints to accommodate various hardware deployments. We propose a novel approach, YOCO-BERT, to achieve compress once and deploy everywhere. Compared with state-of-the-art algorithms, YOCO-BERT provides more compact models, yet achieving 2.1%-4.5% average accuracy improvement on the GLUE benchmark.
  arXiv  Detail & Related papers  (2021-06-04T12:17:44Z)
• Evolutionary Gait Transfer of Multi-Legged Robots in Complex Terrains [14.787379075870383]
  This paper proposes a transfer learning-based evolutionary framework for gait optimization, named Tr-GO. The idea is to initialize a high-quality population by using the technique of transfer learning, so any kind of population-based optimization algorithms can be seamlessly integrated into this framework. The experimental results show the effectiveness of the proposed framework for the gait optimization problem based on three multi-objective evolutionary algorithms.
  arXiv  Detail & Related papers  (2020-12-24T16:41:36Z)
• New Fusion Algorithm provides an alternative approach to Robotic Path planning [0.0]
  This paper presents a new and efficient fusion algorithm for solving the path planning problem in a custom 2D environment. The new fusion algorithm is feasible and superior in smoothness performance and can satisfy as a time-efficient and cheaper alternative to conventional A* strategies of path planning.
  arXiv  Detail & Related papers  (2020-06-06T17:52:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.