Unverified50% confidenceFactExact time
Cord models "given the prompt and the current partial response, selecting a residual coefficient to modulate the revealing order" as a contextual bandit problem, where the action space consists of low-dimensional residual coefficients rather than specific tokens, and the reward is taken from a sequence-level metric after the entire sequence has been generated.
1
Sources
50%
Confidence
Long-term
Relevance
10/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedChunkAct elevates action chunking from low-level continuous control to the agentic planning level; the object of chunking is the sequence of primitive calls, and the chunk boundaries are determined by decision points rather than fixed time windows65% similarVerifiedRoPE (Rotary Position Embedding) injects positional information into attention computation in the form of a rotation matrix, preserving relative positional relationships across arbitrary sequence lengths.65% similarUnverifiedContextual bandit is a class of sequential decision-making frameworks in reinforcement learning: the agent observes contextual features each round, selects an action and receives only an immediate reward, without involving the step-by-step credit assignment problem and without requiring temporal backup estimation of a value function.62% similarUnverified该项目将博弈问题建模为监督分类任务，神经网络输入为编码后的棋盘状态，输出为9个格子中最佳落子位置的概率分布，通过交叉熵损失学习模仿Minimax决策62% similarUnverifiedThe core idea of packrat parsing is to cache the result of each parser at a specific input position during parsing, so that on backtracking the cache can be reused directly, thereby guaranteeing linear time complexity.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1114435API
curl https://kongchang.com/api/v1/knowledge/claims/1114435MCP
get_claim(id=1114435)