Reinforcement learning

Gradient-based Planning for World Models at Longer Horizons

grasp-results-table table { font-size: 0. 875rem; line-height: 1.

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

Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective

Continuously hardening ChatGPT Atlas against prompt injection

OpenAI is strengthening ChatGPT Atlas against prompt injection attacks using automated red teaming trained with reinforcement learning. This proactive discover-and-patch loop helps identify novel exploits early and harden the browser agent’s defenses as AI becomes more agentic.

From DeepSeek V3 to V3.2: Architecture, Sparse Attention, and RL Updates

Understanding How DeepSeek's Flagship Open-Weight Models Evolved

RL without TD learning

In this post, I’ll introduce a reinforcement learning (RL) algorithm based on an “alternative” paradigm: divide and conquer . Unlike traditional methods, this algorithm is not based on temporal difference (TD) learning (which has scalability challenges ), and scales well to long-horizon tasks.

Kimina-Prover-RL

Kimina-Prover-RL

Kimina-Prover: Applying Test-time RL Search on Large Formal Reasoning Models

Kimina-Prover: Applying Test-time RL Search on Large Formal Reasoning Models

Addendum to o3 and o4-mini system card: Codex

Codex is a cloud-based coding agent. Codex is powered by codex-1, a version of OpenAI o3 optimized for software engineering.

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

Finding GPT-4’s mistakes with GPT-4

CriticGPT, a model based on GPT-4, writes critiques of ChatGPT responses to help human trainers spot mistakes during RLHF

Putting RL back in RLHF

Cappy: Outperforming and boosting large multi-task language models with a small scorer

Posted by Yun Zhu and Lijuan Liu, Software Engineers, Google Research Large language model (LLM) advancements have led to a new paradigm that unifies various natural language processing (NLP) tasks within an instruction-following framework. This paradigm is exemplified by recent multi-task LLMs, such as T0 , FLAN , and OPT-IML .

The N Implementation Details of RLHF with PPO

Fine-tune Llama 2 with DPO

StackLLaMA: A hands-on guide to train LLaMA with RLHF

Fine-tuning 20B LLMs with RLHF on a 24GB consumer GPU

Introducing ⚔️ AI vs. AI ⚔️ a deep reinforcement learning multi-agents competition system