Putting RL back in RLHF

The N Implementation Details of RLHF with PPO

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

vLLM V0 to V1: Correctness Before Corrections in RL

Open R1: Update #4

Open R1: Update #3

RL²: Fast reinforcement learning via slow reinforcement learning

Gotta Learn Fast: A new benchmark for generalization in RL

Open R1: Update #2

Spinning Up in Deep RL

We’re releasing Spinning Up in Deep RL, an educational resource designed to let anyone learn to become a skilled practitioner in deep reinforcement learning. Spinning Up consists of crystal-clear examples of RL code, educational exercises, documentation, and tutorials.

Representation and Invariance in Reinforcement Learning

arXiv:2112. 07752v4 Announce Type: replace-cross Abstract: Researchers have formalized reinforcement learning (RL) in different ways.

Mini-R1: Reproduce Deepseek R1 „aha moment“ a RL tutorial

Mechanism-Guided Selective Unlearning for RLVR-Induced Reasoning

We propose MAST (Mechanism-Aligned Selective Targeting), a mechanism-guided method for unlearning RLVR-induced reasoning with substantially lower collateral damage than standard full-parameter updates. In matched SFT/RLVR checkpoints on Qwen2.