Unverified50% confidenceFactExact time
The algorithm proposed in the paper achieves, in adversarial tabular MDPs, regret bounds of Õ(√(HS(H+A)T)) under known transitions and Õ(HS√(AT)) under unknown transitions.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedA linear mixture MDP is a class of function approximation settings in which the transition probability is assumed to be a linear combination of known basis features: P(s'|s,a)=Σφ_i(s'|s,a)θ_i, where φ_i are known features and θ are unknown parameters, allowing the state space to be huge or even continuous while retaining a learnable linear structure.63% similarUnverifiedThe partial derivative of the MSE loss function with respect to parameter W is ∂L/∂W = (2/n) * Xᵀ(XW - y), and the partial derivative with respect to b is ∂L/∂b = (2/n) * Σ(y_pred - y).61% similarUnverified哈达玛矩阵满足正交性条件 H_n · H_n^T = n · I_n，使哈达玛变换可逆且不丢失信息61% similarUnverifiedThe paper assumes access to a generative model of the MDP, meaning the algorithm can query samples for any state-action pair.61% similarUnverifiedThe formalized problem of DT-DRO admits a computationally tractable dual reformulation.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1012964API
curl https://kongchang.com/api/v1/knowledge/claims/1012964MCP
get_claim(id=1012964)