Unverified50% confidenceFactExact time
DreamerV3采用的RSSM（循环状态空间模型）由Danijar Hafner等人提出，将隐状态分解为确定性循环状态和随机隐变量
1
Sources
50%
Confidence
Long-term
Relevance
7/19/2026
First Seen
Sources
LeMario：用超级马里奥训练JEPA世界模型的开源实践
Related Claims
UnverifiedDreamer系列（Hafner等人，2019-2023）核心是循环状态空间模型（RSSM），通过重构观测学习表征，属于生成式方法80% similarUnverifiedDreamerV3 是基于隐空间的世界模型，在压缩的潜在表示空间中进行预测，计算效率更高68% similarVerifiedState space models (SSMs) such as Mamba abandon the attention mechanism and use recurrent structures to achieve linear time complexity sequence modeling.65% similarVerifiedMamba 等基于状态空间模型（SSM）的架构以线性复杂度实现序列建模，更适合实时推理62% similarUnverifiedThe world model of Ha and Schmidhuber employs a three-module architecture: a visual encoder V responsible for perceptual compression, a recurrent neural network M responsible for temporal memory, and a controller C responsible for decision-making.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/564475API
curl https://kongchang.com/api/v1/knowledge/claims/564475MCP
get_claim(id=564475)