Unverified50% confidenceSolutionExact time
In each iteration, GAP-DPO selects preference pairs based on the direction of the utility gradient.
1
Sources
50%
Confidence
Long-term
Relevance
10/2/2026
First Seen
Sources
Related Entities
Related Claims
Unverified基于策略梯度的算法如PPO和GRPO能够处理离散与连续混合的动作空间62% similarUnverifiedMulti-Objective Direct Preference Optimization (MODPO) introduces an "objective weight" parameter, through which adjusting the weights can form a continuous trade-off spectrum among multiple competing objectives.60% similarUnverifiedMulti-channel retrieval simultaneously fetches candidate results through multiple different retrieval channels and then performs fusion ranking to maximize recall rate.58% similarUnverifiedThe multi-step chained working mode of edge agents causes single-inference latency to be amplified across multiple steps.58% similarUnverifiedIn automatic differentiation, when a variable affects the loss function through multiple computation paths, the gradients from each path must be summed (gradient accumulation).57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/966741API
curl https://kongchang.com/api/v1/knowledge/claims/966741MCP
get_claim(id=966741)