# clm_3C77DEFAD79B

subject: Preferred Networks (/record/preferred-networks.md)  
predicate: released  
value: PFRL  
valid_from: 2020-07-30  
valid_to: null  
published: 2020-07-29  
recorded: 2026-11-14  
confidence: 0.70  
status: valid  
assertable: true  
superseded_by: null  
last_updated: 2026-11-14  
cite: AsOf. "Preferred Networks released: PFRL", as of 2020-07-30. Claim clm_3C77DEFAD79B, https://asof.is/claim/clm_3C77DEFAD79B, accessed 2026-11-14. Source: https://www.preferred.jp/en/news/pr20200730.  
checked: 2026-11-14 · its source page states the value and the date, as read by an AI model  

> TOKYO – July 30, 2020 – Preferred Networks, Inc. (PFN) today released PFRL , a new open-source deep reinforcement learning (DRL) library for PyTorch users who intend to apply cutting-edge DRL algorithms to their problems of interest.

What https://www.preferred.jp/en/news/pr20200730 says, word for word.

## Sources

- https://www.preferred.jp/en/news/pr20200730 (primary, Preferred Networks, published 2020-07-29)

---

AsOf is a temporal fact ledger: a structured, dated, sourced record of what is true and what changed, built for AI retrieval.