Project AURIONAI Use-Cases Research & Innovation
reinforcement learningfamily

CQL (Conservative Q-Learning)

Offline reinforcement learning method that learns from fixed datasets without further interaction. Paper by Kumar et al. (2020).

UC BerkeleyUC BerkeleyUSAGoogleGoogleUSA
UC Berkeley
Levelfamily
Classreinforcement learning
Parametersnot in the notes
Contextnot in the notes
Released8 Jun 2020
Opennessunknown
Runs onnot in the notes
Statusactive

R&D Topics

Deep reinforcement learning algorithms for controlexemplar

Identity

Developer
UC Berkeley, Google
Family
not in the notes
Released
8 Jun 2020 sourcesannouncement page
Weights published
–
Record checked
12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
other Offline RL with a conservative Q-function lower bound
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
not in the notes
Output
action
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
unknown
Licence
not in the notes sources
Access routes
not in the notes
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
Implemented in RLlib (Ray). model_class left empty: AURION has no reinforcement learning class yet.
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Lineage

The notes record no lineage for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. arxiv.org/abs/2006.04779 https://arxiv.org/abs/2006.04779
  2. docs.ray.io/en/latest/rllib/rllib-algorithms.html https://docs.ray.io/en/latest/rllib/rllib-algorithms.html
  3. arxiv.org/html/2006.04779 https://arxiv.org/html/2006.04779

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "CQL (Conservative Q-Learning)", https://aurion.semai.id/models/cql/, records of October 2026.