Unverified50% confidenceFactExact time
WAS-PO (Whitened Advantage Summation Policy Optimization) is a multi-reward reinforcement learning method that, after normalizing advantages and before the weighted sum, first whitens the advantages with Σ^{-1/2}, so that the weights act on the decorrelated components.
1
Sources
50%
Confidence
Long-term
Relevance
11/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDPO uses a mathematical transformation to equivalently rewrite the "reward maximization + KL constraint" objective as a simple classification loss, requiring no reward model and no reinforcement learning loop, and alignment can be completed with supervised learning alone.61% similarUnverifiedScore matching is one of the core techniques for training diffusion models, with the score function defined as the gradient of the log probability density ∇_x log p_t(x).58% similarUnverifiedDirect preference optimization (DPO) shows that under a specific reward structure, the RL objective can be equivalently transformed into likelihood maximization over a certain target distribution, thereby bypassing an explicit reward model and policy gradients.58% similarVerifiedDPO (Direct Preference Optimization) is an alignment method proposed in 2023 that can skip reward model training and directly optimize the policy model from human preference data.58% similarUnverifiedMoPD (Model Parameter Diffusion/Merging) is a technique for injecting the capabilities of a lightweight specialized model into a main model, enabling the transfer of behavioral preferences learned by the teacher model without full retraining.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1130531API
curl https://kongchang.com/api/v1/knowledge/claims/1130531MCP
get_claim(id=1130531)