AI Trace
Productivity AutomationVerified

Reviewed and published by trentmaziarz, May 11, 2026. Discovered and drafted by our automated research pipeline.

Sony Interactive Entertainment uses deep learning to build autonomous gameplay agents that can play PS5 games under human-equivalent conditions, automating system software function tests to identify defects earlier in development.

Details

Presented at CEDEC 2024 (Computer Entertainment Developers Conference), the system combines two AI components: a Replay Agent that reproduces recorded button sequences, and an Imitation Agent trained via imitation learning on human gameplay footage to handle unpredictable scenarios in real time. The system uses on-screen information only, replicating ordinary user conditions. It was developed to address the growing cost of manual QA testing as games scale in complexity. Sony describes the goal as lowering testing costs and identifying defects earlier in the development cycle.

Products affected

PlayStation 5 system software

Sources & Evidence

Cite this record

Trace Foundation. (2026). Sony Interactive Entertainment: Sony Interactive Entertainment uses deep learning to build autonomous gameplay agents that can play PS5 games under human-equivalent conditions, automating system software function tests to identify defects earlier in development (data as of 2026-05-11) [Data set record]. AI Trace. https://www.aitrace.org/r/practice/12f61cea-5eaa-4e7a-905d-aa13d5b0e1d3. Accessed October 5, 2026.

Stable link
https://www.aitrace.org/r/practice/12f61cea-5eaa-4e7a-905d-aa13d5b0e1d3
Data as of
May 11, 2026
Last verified
Not recorded

How to cite AI Trace

Other practices by Sony Interactive Entertainment

Have evidence about Sony Interactive Entertainment's AI practices? Submit a report.

Report a Sighting →