What is recorded here?
Augmented Bellman regression with a conservative Q-value penalty, contrasting policy/proposal actions with data actions to reduce value overestimation during offline learning.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
The tighter objective bounds policy-expected value under stated support, regularization and policy-change assumptions; it is not a pointwise lower bound for every action. Main tabular statements and practical nonlinear optimization are distinct; empirical results do not certify universal safe improvement.
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
Aviral Kumar; Aurick Zhou; George Tucker; 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
CQL: conservative value regularization for offline reinforcement learning
Augmented Bellman regression with a conservative Q-value penalty, contrasting policy/proposal actions with data actions to reduce value overestimation during offline learning.
Scientific scope
The tighter objective bounds policy-expected value under stated support, regularization and policy-change assumptions; it is not a pointwise lower bound for every action. Main tabular statements and practical nonlinear optimization are distinct; empirical results do not certify universal safe improvement.
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
Aviral Kumar; Aurick Zhou; George Tucker; 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.