Evolution strategies as a scalable alternative to reinforcement learning

Memory Efficient RL | Unsloth Documentation

We're excited to introduce more efficient reinforcement learning (RL) in Unsloth with multiple algorithmic advancements:

Training AI Agents with RL | Unsloth Documentation

Learn how to train AI agents for real-world tasks using Reinforcement Learning (RL).

#Exploration: A Study of Count-Based Exploration for Deep...

Count-based exploration algorithms are known to perform near-optimally when used in conjunction with tabular reinforcement learning (RL) methods for solving small discrete Markov decision...

Reward is not the optimization target — LessWrong

TurnTrout discusses a common misconception in reinforcement learning: that reward is the optimization target of trained agents. He argues reward is b…

LukeW | The Evolution of AI Products

At this point, the use of artificial intelligence and machine learning models in software has a long history. But the past three years really accelerated the ev...

Position: Don't Just "Fix it in Post": A Science of AI Must Study Training Dynamics

What would it mean to have a scientific understanding of AI? Models are not static objects: they are snapshots of time-evolving processes shaped by data, objectives, architectures, and optimization dynamics. Yet much of AI research treats models as fixed artifacts, analyzing behaviors after training rather than asking why they emerge. This position paper argues that a science of AI must move beyond post-hoc fixes and study the training dynamics that produce model behavior. Such a science should support progressively stronger forms of understanding: predicting outcomes from early training signals, intervening when trajectories go wrong, and ultimately designing training procedures that more reliably produce desired properties. Scaling laws have made prediction routine for loss; the challenge is extending this success to capabilities, biases, robustness, and safety-relevant behaviors. We articulate requirements for such theories grounded in the history and philosophy of science, examine progress in mechanistic interpretability, fairness, memorization, and simplicity bias, and identify concrete open problems.

Reinforcement Learning from Human Feedback

The authoritative guide for Reinforcement learning from human feedback, alignment, and post-training LLMs. Aligning AI models to human preferences helps them become safer, smarter, easier to use, and tuned to the exact style the creator desires. Reinforcement Learning From Human Feedback (RHLF) is the process for using human responses to a model’s output to shape its alignment, and therefore its behavior. In Reinforcement Learning from Human Feedback, author Nathan Lambert blends diverse perspectives from fields like philosophy and economics with the core mathematics and computer science of RLHF to provide a practical guide you can use to apply RLHF to your models. In Reinforcement Learning from Human Feedback you’ll discover: How today’s most advanced AI models are taught from human feedback How large-scale preference data is collected and how to improve your data pipelines A comprehensive overview with derivations and implementations for the core policy-gradient methods used to train AI models with reinforcement learning (RL) Direct Preference Optimization (DPO), direct alignment algorithms, and simpler methods for preference finetuning How RLHF methods led to the current reinforcement learning from verifiable rewards (RLVR) renaissance Tricks used in industry to round out models, from product, character or personality training, AI feedback, and more How to approach evaluation and how evaluation has changed over the years Standard recipes for post-training combining more methods like instruction tuning with RLHF Behind-the-scenes stories from building open models like Llama-Instruct, Zephyr, Olmo, and Tülu After ChatGPT used RLHF to become production-ready, this foundational technique exploded in popularity. In Reinforcement Learning from Human Feedback, AI expert Nathan Lambert gives a true industry insider's perspective on modern RLHF training pipelines, and their trade-offs. Using hands-on experiments and mini-implementations, Nathan clearly and concisely introduces the alignment techniques that can transform a generic base model into a human-friendly tool.

Scalable decision-making for games of imperfect information

Real-world decision-making generally involves hidden information, that is, information that is unknown to one agent but possessed by another. Unfortunately, the presence of large amounts of hidden information renders established reinforcement learning and search approaches ineffective. Even with multimillion-dollar industrial research efforts1, top-human-level play at Stratego—a board wargame with hidden information on a massive scale—has remained beyond the reach of artificial intelligence (AI). Here we introduce Ataraxos, an AI for Stratego based on general techniques that we developed for both self-play reinforcement learning and test-time search under hidden information. Ataraxos defeated the most decorated human Stratego player of all time by a large margin—achieving, to our knowledge, the first superhuman result in the game’s history—while consuming orders of magnitude less compute and data than previous efforts. Using the same techniques, we built a superhuman AI for Barrage Stratego and state-of-the-art AIs for Hanabi and dou dizhu, all with low cost and high sample efficiency. The success of this approach across adversarial, cooperative and team games establishes a design pattern for reinforcement learning and search that is effective under large amounts of hidden information, a longstanding desideratum of the field of strategic decision-making.

Why Tool AIs Want to Be Agent AIs

AIs limited to pure computation (Tool AIs) supporting humans, will be less intelligent, efficient, and economically valuable than more autonomous reinforcement-learning AIs (Agent AIs) who act on their own and meta-learn, because all problems are reinforcement-learning problems.

Lightweight Guide to understanding GRPO and RL principles

A beginner-friendly guide to Group Relative Policy Optimization (GRPO) training workflow without assuming prior RL knowledge.

Hybrid social learning in human-algorithm cultural transmission

Humans are impressive social learners. Researchers of cultural evolution have studied the many biases shaping cultural transmission by selecting who we copy from and what we copy. One hypothesis is that with the advent of superhuman algorithms a hybrid type of cultural transmission, namely from algorithms to humans, may have long-lasting effects on human culture. We suggest that algorithms might show (either by learning or by design) different behaviours, biases and problem-solving abilities than their human counterparts. In turn, algorithmic-human hybrid problem solving could foster better decisions in environments where diversity in problem-solving strategies is beneficial. This study asks whether algorithms with complementary biases to humans can boost performance in a carefully controlled planning task, and whether humans further transmit algorithmic behaviours to other humans. We conducted a large behavioural study and an agent-based simulation to test the performance of transmission chains with human and algorithmic players. We show that the algorithm boosts the performance of immediately following participants but this gain is quickly lost for participants further down the chain. Our findings suggest that algorithms can improve performance, but human bias may hinder algorithmic solutions from being preserved. This article is part of the theme issue ‘Emergent phenomena in complex physical and socio-technical systems: from cells to societies’.

Osmosis | Forward Deployed Reinforcement Learning Platform

Osmosis is a forward-deployed reinforcement learning platform that helps companies train task-specific AI models that outperform foundation models at a fraction of the cost. Build, deploy, and continuously improve intelligent systems with hands-on integration and real-time feedback.

OpenPipe/ART

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

OpenPipe/ART

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

OpenPipe/ART

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!