FactorSim: Generative Simulation via Factorized Representation

• URL: http://arxiv.org/abs/2409.17652v2
• Date: Mon, 11 Nov 2024 08:16:40 GMT
• Title: FactorSim: Generative Simulation via Factorized Representation
• Authors: Fan-Yun Sun, S. I. Harini, Angela Yi, Yihan Zhou, Alex Zook, Jonathan Tremblay, Logan Cross, Jiajun Wu, Nick Haber,
• Abstract summary: We introduce FACTORSIM that generates full simulations in code from language input that can be used to train agents. For evaluation, we introduce a generative simulation benchmark that assesses the generated simulation code's accuracy and effectiveness in facilitating zero-shot transfers in reinforcement learning settings. We show that FACTORSIM outperforms existing methods in generating simulations regarding prompt alignment (e.g., accuracy), zero-shot transfer abilities, and human evaluation.
• Score: 14.849320460718591
• License:
• Abstract: Generating simulations to train intelligent agents in game-playing and robotics from natural language input, from user input or task documentation, remains an open-ended challenge. Existing approaches focus on parts of this challenge, such as generating reward functions or task hyperparameters. Unlike previous work, we introduce FACTORSIM that generates full simulations in code from language input that can be used to train agents. Exploiting the structural modularity specific to coded simulations, we propose to use a factored partially observable Markov decision process representation that allows us to reduce context dependence during each step of the generation. For evaluation, we introduce a generative simulation benchmark that assesses the generated simulation code's accuracy and effectiveness in facilitating zero-shot transfers in reinforcement learning settings. We show that FACTORSIM outperforms existing methods in generating simulations regarding prompt alignment (e.g., accuracy), zero-shot transfer abilities, and human evaluation. We also demonstrate its effectiveness in generating robotic tasks.

Related papers

• BeSimulator: A Large Language Model Powered Text-based Behavior Simulator [28.112491177744783]
  We introduce BeSimulator as an attempt towards behavior simulation in the context of text-based environments. BeSimulator can generalize across scenarios and achieve long-horizon complex simulation.
  arXiv  Detail & Related papers  (2024-09-24T08:37:04Z)
• Semantic Capability Model for the Simulation of Manufacturing Processes [38.69817856379812]
  Simulations offer opportunities in the examination of manufacturing processes. A combination of different simulations is necessary when the outputs of one simulation serve as the input parameters for another, resulting in a sequence of simulations. An information model is introduced, which represents simulations, their capabilities to generate certain knowledge, and their respective quality criteria.
  arXiv  Detail & Related papers  (2024-08-15T09:28:08Z)
• DrEureka: Language Model Guided Sim-To-Real Transfer [64.14314476811806]
  Transferring policies learned in simulation to the real world is a promising strategy for acquiring robot skills at scale. In this paper, we investigate using Large Language Models (LLMs) to automate and accelerate sim-to-real design. Our approach is capable of solving novel robot tasks, such as quadruped balancing and walking atop a yoga ball.
  arXiv  Detail & Related papers  (2024-06-04T04:53:05Z)
• DiffGen: Robot Demonstration Generation via Differentiable Physics Simulation, Differentiable Rendering, and Vision-Language Model [72.66465487508556]
  DiffGen is a novel framework that integrates differentiable physics simulation, differentiable rendering, and a vision-language model. It can generate realistic robot demonstrations by minimizing the distance between the embedding of the language instruction and the embedding of the simulated observation. Experiments demonstrate that with DiffGen, we could efficiently and effectively generate robot data with minimal human effort or training time.
  arXiv  Detail & Related papers  (2024-05-12T15:38:17Z)
• Informal Safety Guarantees for Simulated Optimizers Through Extrapolation from Partial Simulations [0.0]
  Self-supervised learning is the backbone of state of the art language modeling. It has been argued that training with predictive loss on a self-supervised dataset causes simulators.
  arXiv  Detail & Related papers  (2023-11-29T09:32:56Z)
• From Natural Language to Simulations: Applying GPT-3 Codex to Automate Simulation Modeling of Logistics Systems [0.0]
  This work is the first attempt to apply Natural Language Processing to automate the development of simulation models of systems vitally important for logistics. We demonstrated that the framework built on top of the fine-tuned GPT-3 Codex, a Transformer-based language model, could produce functionally valid simulations of queuing and inventory control systems given the verbal description.
  arXiv  Detail & Related papers  (2022-02-24T14:01:50Z)
• Deep Bayesian Active Learning for Accelerating Stochastic Simulation [74.58219903138301]
  Interactive Neural Process (INP) is a deep active learning framework for simulations and with active learning approaches. For active learning, we propose a novel acquisition function, Latent Information Gain (LIG), calculated in the latent space of NP based models. The results demonstrate STNP outperforms the baselines in the learning setting and LIG achieves the state-of-the-art for active learning.
  arXiv  Detail & Related papers  (2021-06-05T01:31:51Z)
• A User's Guide to Calibrating Robotics Simulators [54.85241102329546]
  This paper proposes a set of benchmarks and a framework for the study of various algorithms aimed to transfer models and policies learnt in simulation to the real world. We conduct experiments on a wide range of well known simulated environments to characterize and offer insights into the performance of different algorithms. Our analysis can be useful for practitioners working in this area and can help make informed choices about the behavior and main properties of sim-to-real algorithms.
  arXiv  Detail & Related papers  (2020-11-17T22:24:26Z)
• Reactive Long Horizon Task Execution via Visual Skill and Precondition Models [59.76233967614774]
  We describe an approach for sim-to-real training that can accomplish unseen robotic tasks using models learned in simulation to ground components of a simple task planner. We show an increase in success rate from 91.6% to 98% in simulation and from 10% to 80% success rate in the real-world as compared with naive baselines.
  arXiv  Detail & Related papers  (2020-11-17T15:24:01Z)
• Integrating Machine Learning with HPC-driven Simulations for Enhanced Student Learning [0.0]
  We develop a web application that supports both HPC-driven simulation and the ML surrogate methods to produce simulation outputs. The evaluation of the tool via in-classroom student feedback and surveys shows that the ML-enhanced tool provides a dynamic and responsive simulation environment.
  arXiv  Detail & Related papers  (2020-08-24T22:48:21Z)
• Point Cloud Based Reinforcement Learning for Sim-to-Real and Partial Observability in Visual Navigation [62.22058066456076]
  Reinforcement Learning (RL) represents powerful tools to solve complex robotic tasks. RL does not work directly in the real-world, which is known as the sim-to-real transfer problem. We propose a method that learns on an observation space constructed by point clouds and environment randomization.
  arXiv  Detail & Related papers  (2020-07-27T17:46:59Z)

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.