Unverified50% confidenceSolutionExact time
Decision Transformer将离线轨迹数据建模为因果序列生成问题，通过引入回报条件使模型能够在不与环境交互的情况下从静态数据集学习条件策略
1
Sources
50%
Confidence
Long-term
Relevance
7/19/2026
First Seen
Sources
Related Claims
UnverifiedDecision Transformer 于 2021 年提出，将强化学习问题重新表述为序列建模问题，使用 Transformer 架构对（回报、状态、动作）序列进行自回归预测77% similarUnverifiedFew-shot prompting leverages the in-context learning capability of the Transformer architecture, allowing the model to infer the expected output format from in-context examples alone without updating its parameters.77% similarUnverifiedThe hallucination phenomenon in large models is rooted in the autoregressive generation mechanism of Transformers, where the model learns probability distributions through the Next Token Prediction task during the pre-training phase.75% similarUnverifiedIn the Transformer architecture, there is an approximately linear relationship between model parameter count and inference latency.73% similarUnverifiedThe Transformer model is a purely sequence-to-sequence mapping function whose parameters are completely static during inference, with no mechanism to actively probe the state of the external environment during inference.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/563183API
curl https://kongchang.com/api/v1/knowledge/claims/563183MCP
get_claim(id=563183)