arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.04715cs.LGcs.AI
收藏

基于概率的梦境学习用于世界模型

Probabilistic Dreaming for World Models

Yale University(耶鲁大学)

Gavin Wong

AI总结:

本文提出基于概率的梦境学习方法,通过并行探索潜在状态和保持不同假设,提升世界模型的学习效率和稳定性。

摘要:

梦境学习使智能体能够从想象的经历中学习,从而更鲁棒且样本高效地学习世界模型。在本工作中,我们考虑了对最新状态的Dreamer模型进行改进,采用概率方法实现:(1)并行探索许多潜在状态;(2)在互斥的未来保持不同的假设,同时保留连续潜在变量的 desirable 梯度性质。在MPE SimpleTag领域评估中,我们的方法在得分上比标准Dreamer提高了4.5%,并且每集回报的方差降低了28%。我们还讨论了限制和未来工作的方向,包括最优超参数(如粒子数K)如何随环境复杂性变化,以及如何在世界模型中捕捉认知不确定性。

英文摘要:

"Dreaming" enables agents to learn from imagined experiences, enabling more robust and sample-efficient learning of world models. In this work, we consider innovations to the state-of-the-art Dreamer model using probabilistic methods that enable: (1) the parallel exploration of many latent states; and (2) maintaining distinct hypotheses for mutually exclusive futures while retaining the desirable gradient properties of continuous latents. Evaluating on the MPE SimpleTag domain, our method outperforms standard Dreamer with a 4.5% score improvement and 28% lower variance in episode returns. We also discuss limitations and directions for future work, including how optimal hyperparameters (e.g. particle count K) scale with environmental complexity, and methods to capture epistemic uncertainty in world models.

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。

↑