Adaptive Agent
No estimate
No hardware requirements for this model
The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.
On record
Full specification
Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.
Origin
Who built this model, where, and when it was published.
- Organisation
- DeepMind
- Organisation type
- Industry
- Country
- United Kingdom of Great Britain and Northern Ireland
- Published
- 18 January 2023
- Authors
- Adaptive Agent Team, Jakob Bauer, Kate Baumli, Satinder Baveja, Feryal Behbahani, Avishkar Bhoopchand, Nathalie Bradley-Schmieg, Michael Chang, Natalie Clay, Adrian Collister, Vibhavari Dasagi, Lucy Gonzalez, Karol Gregor, Edward Hughes, Sheleem Kashem, Maria Loks-Thompson, Hannah Openshaw, Jack Parker-Holder, Shreya Pathak, Nicolas Perez-Nieves, Nemanja Rakicevic, Tim Rocktäschel, Yannick Schroec…
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Games
- Task
- Open ended play
- Approach
- Reinforcement learning
Size
How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.
- Parameters
- 533M
- Training data
- tokens
Table D.9
Training compute
The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.
- Training compute
- 2.8 × 10²¹ FLOP
- How it was established
- Hardware
"AdA was implemented using JAX (Bradbury et al., 2018) and the DeepMind JAX Ecosystem (Babuschkin et al., 2020) and trained on 64 Google TPUv3 devices. The wall-clock time for training this version of AdA from scratch was approximately 5 weeks: 1 week to train the teacher, and 4 weeks to train AdA" 64 * 123 teraflop/s * 35 days * 24 * 3600 * 0.4 = 9.5e21 This might be for all single-agent experiments in the paper, or just for the 76M model in Table D.1, I'm not sure. In Table E.2, the 533M-pa…
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Training hardware
- Google TPU v3
- Wall-clock time
- 840 hours (35 days)
5 weeks. Possible that this is for multiple models
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Closed — provider access only
- Model access
- Unreleased
- Training code
- Unreleased
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Speculative
- Citations
- 157
Sources
Where this record came from and when it was last checked.
- Reference
- Human-Timescale Adaptation in an Open-Ended Task Space
- Last updated
- 25 May 2026
What the numbers mean
About this model
Adaptive Agent was published by DeepMind, in United Kingdom of Great Britain and Northern Ireland, in January 2023. The organisation is categorised as industry.
It works in Games, and is recorded as doing open ended play.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
Training and provenance
The training run consumed about 2.8 × 10²¹ FLOP, on Google TPU v3. That figure describes the cost of creating it and has no bearing on how quickly it generates text.
Answers
Adaptive Agent — common questions
What GPU do I need to run Adaptive Agent?
None. Adaptive Agent is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.
Is Adaptive Agent open source?
No. Adaptive Agent has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does Adaptive Agent have?
Adaptive Agent has 533M parameters. Table D.9. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.
Who created Adaptive Agent?
Adaptive Agent was published by DeepMind, based in United Kingdom of Great Britain and Northern Ireland, categorised as industry.
When was Adaptive Agent released?
Adaptive Agent was published in January 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
What is Adaptive Agent used for?
Adaptive Agent works in Games, and is recorded as handling open ended play. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.
How much compute was used to train Adaptive Agent?
Around 2.8 × 10²¹ FLOP, on Google TPU v3. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.
The other direction
Looking at it from the other side?
This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.