Unverified50% confidenceFactExact time
In each Bellman update, DFQI simultaneously updates the target Q-function and borrows source information, achieving tighter coupling.
1
Sources
50%
Confidence
Long-term
Relevance
11/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedFor heterogeneous transition kernels, DFQI automatically adjusts the contribution of source information through weighted aggregation, avoiding negative transfer.72% similarUnverifiedDFQI introduces an L1 penalty term in the fitted Q-iteration framework, pulling the target coefficients toward a weighted combination of the source coefficients, with weights determined adaptively from the data.72% similarUnverifiedThe paper proposes Direct Transfer Fitted Q-Iteration (DFQI), which directly incorporates source-environment information into target value-function learning through a joint estimation framework.69% similarUnverifiedTheoretical analysis shows that, under certain regularity conditions, the target Q-function estimation and policy value convergence rates of DFQI are comparable to estimators that use only target data, while it can effectively exploit source data to reduce variance.69% similarUnverifiedCompared with baselines (such as using only target data, simple data mixing, etc.), DFQI shows advantages in both policy return and stability.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1129558API
curl https://kongchang.com/api/v1/knowledge/claims/1129558MCP
get_claim(id=1129558)