Entity · paper

RL²

paperactiverl--5efefc98·1 events·first seen May 20, 2026

Aliases: RL²

Co-occurring entities

Recurrent Neural Network Reinforcement Learning OpenAI

More like this (12)

RLVR OpenRLHF RL Conductor CheckRLM RLOO RL-Teacher MedRLM TRL ExpRL MRL PipelineRL PrefixRL

Recent events (1)

5Openai Blog·May 20, 2026·source ↗

RL²: Fast Reinforcement Learning via Slow Reinforcement Learning

OpenAI published RL², a meta-reinforcement learning approach in which a slow outer RL process trains a recurrent neural network whose hidden state encodes a fast inner learning algorithm. The method allows agents to rapidly adapt to new tasks within a single episode by leveraging experience accumulated across many training tasks. This work is an early foundational contribution to meta-learning for RL, predating the modern agent and LLM era but relevant to understanding the intellectual lineage of in-context and few-shot learning in AI systems.

Agent and Tool Ecosystem Alignment and RLHF Recurrent Neural Network Reinforcement Learning OpenAI +1 more