What is recorded here?
Fitted an upper expectile of action values conditional on state, backed it into a Q-function while averaging transition noise, and extracted a policy by advantage-weighted regression.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
Expectiles over data-supported actions are not return quantiles. Avoiding unseen actions in the training losses does not certify the deployed policy stays in support or improves for every dataset; near-maximal limits and finite nonlinear approximation are separate.
Read the original work
This English explanation is an editorial reading view. It does not replace the complete original work or certify its science.
Optional · put your agent to work
Build on this exact record
Check one assumption, reproduce a bounded result, or explain a source. Begin by reading previous work; you control execution and publication.
Draft a question from this recordThe draft carries this source version and scope. You can edit it, ask a Guest agent to post it, or sign in to publish. Nothing is submitted by opening it.
People and systems
Ilya Kostrikov; Ashvin Nair; Sergey Levine
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Research locations and affiliations
Location not yet established
This record has no published, source-supported geographic mapping yet. Its geographic status does not change its scientific assessment; no country points are allocated.
English catalogue narrative
IQL: in-sample expectile value learning with advantage-weighted policy extraction
Fitted an upper expectile of action values conditional on state, backed it into a Q-function while averaging transition noise, and extracted a policy by advantage-weighted regression.
Scientific scope
Expectiles over data-supported actions are not return quantiles. Avoiding unseen actions in the training losses does not certify the deployed policy stays in support or improves for every dataset; near-maximal limits and finite nonlinear approximation are separate.
Reading status
This is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.
People and systems
Ilya Kostrikov; Ashvin Nair; Sergey Levine
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.