FactorSim：基于因子化表示的生成式仿真
FactorSim: Generative Simulation via Factorized Representation
AI总结：
FactorSim提出一种基于因子化表示的生成式仿真方法，能从语言输入生成完整仿真代码，用于训练智能体，在提示对齐、零样本迁移和机器人任务生成上优于现有方法。
摘要：
从自然语言输入、用户输入或任务文档中生成仿真以训练游戏和机器人领域的智能体，仍然是一个开放性的挑战。现有方法仅关注该挑战的某一部分，例如生成奖励函数或任务超参数。与以往工作不同，我们提出了FACTORSIM，它能够根据语言输入以代码形式生成完整的仿真，这些仿真可用于训练智能体。利用编码仿真特有的结构模块性，我们提出使用因子化部分可观测马尔可夫决策过程表示，从而在生成过程的每一步减少上下文依赖性。为了评估，我们引入了一个生成式仿真基准，该基准评估生成的仿真代码在促进强化学习设置中零样本迁移方面的准确性和有效性。我们表明，FACTORSIM在生成仿真方面优于现有方法，具体体现在提示对齐（如准确性）、零样本迁移能力和人工评估方面。我们还展示了其在生成机器人任务中的有效性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
