Hacker News with Generative AI: Reinforcement Learning

Launch HN: Augento (YC W25) – Fine-tune your agents with reinforcement learning (ycombinator.com)
Hi HN, we’re the cofounders of Augento (https://augento.ai/). We’re building Deepseek R1-like fine-tuning as a service. You connect your agent, tell us when it’s right or wrong, and we deliver an LLM optimized for that agent.
Machine Learning, Reinforcement Learning, Startups, AI, SaaS
94 points by lmeierhoefer 1 day ago | 57 comments
I Built Faster Reinforcement Learning in C# Solo Than Teams Did with Python (rlmatrix.com)
The question comes relentlessly: “Why build reinforcement learning in C#?” Behind this query lies an unspoken assumption that serious machine learning happens exclusively in Python. This perspective reveals a fundamental disconnect between academic ML researchers with their sprawling Python scripts and those of us solving real industrial problems.
Reinforcement Learning, Programming Languages, C#, Python, Machine Learning
13 points by adriansieradzki 4 days ago | 2 comments
A (Long) Peek into Reinforcement Learning (lilianweng.github.io)
A couple of exciting news in Artificial Intelligence (AI) has just happened in recent years. AlphaGo defeated the best professional human player in the game of Go. Very soon the extended algorithm AlphaGo Zero beat AlphaGo by 100-0 without supervised learning on human knowledge. Top professional game players lost to the bot developed by OpenAI on DOTA2 1v1 competition. After knowing these, it is pretty hard not to be curious about the magic behind these algorithms — Reinforcement Learning (RL).
Artificial Intelligence, Machine Learning, Reinforcement Learning
159 points by Brysonbw 10 days ago | 16 comments
Understanding R1-Zero-Like Training: A Critical Perspective (github.com/sail-sg)
To understand R1-Zero-like training, we critically examine two core components: base models and reinforcement learning. We highlight our findings below.
Machine Learning, Reinforcement Learning, Research, Artificial Intelligence
160 points by pama 10 days ago | 21 comments
Hunyuan T1 Mamba Reasoning model beats R1 on speed and metrics (tencent.github.io)
Reinforcement learning has pioneered a new Scaling paradigm in the post-training phase of large language models, a breakthrough that is increasingly attracting attention from the industry.
Artificial Intelligence, Reinforcement Learning
26 points by vessenes 11 days ago | 2 comments
Legged Locomotion Meets Skateboarding (umich-curly.github.io)
This paper introduces Discrete-time Hybrid Automata Learning (DHAL), a framework using on-policy Reinforcement Learning to identify and execute mode-switching without trajectory segmentation or event function learning.
Robotics, Reinforcement Learning, Machine Learning
156 points by jam 11 days ago | 37 comments
Mathematical Foundations of Reinforcement Learning (github.com/MathFoundationRL)
This textbook has received 5,000+ stars! Glad that it is helpful to many readers.
Reinforcement Learning, Mathematics, Computer Science, Education
424 points by ibobev 22 days ago | 43 comments
Reinforcement Learning in less than 400 lines of C (github.com/antirez)
This code implements a neural network that learns to play tic-tac-toe using reinforcement learning, just playing against a random adversary, in under 400 lines of C code, without any external library used.
Reinforcement Learning, Programming, C Programming, Tic-Tac-Toe
10 points by antirez 22 days ago | 4 comments
Show HN: Llama-8B Teaches Itself Baby Steps to Deep Research Using RL (github.com/dCaples)
Autonomously train research-agent LLMs on custom data using reinforcement learning and self-verification.
Reinforcement Learning, Research, Artificial Intelligence, Open Source
39 points by diegocaples 22 days ago | 3 comments
All Roads Lead to Likelihood: The Value of Reinforcement Learning in Fine-Tuning (arxiv.org)
From a first-principles perspective, it may seem odd that the strongest results in foundation model fine-tuning (FT) are achieved via a relatively complex, two-stage training procedure.
Machine Learning, Reinforcement Learning, Fine-Tuning, Foundation Models
3 points by gkswamy98 24 days ago | 0 comments
Using GRPO to Beat o1, o3-mini and R1 at “Temporal Clue” (openpipe.ai)
In this post we’ll discuss how we used Group Relative Policy Optimization (GRPO) to surpass R1, o1, o3-mini, and come within a couple percentage points of Sonnet 3.7 on a reasoning-heavy game called “temporal clue”, while being over 100x cheaper to run at inference time. We’ll include specific lessons learned about task design and hyperparameters we’ve found to work well. And finally, we share the training recipe we used to achieve these results, built on top of torchtune.
Artificial Intelligence, Reinforcement Learning, Game Development, Optimization
199 points by kcorbitt 26 days ago | 55 comments
QwQ-32B: Embracing the Power of Reinforcement Learning (qwenlm.github.io)
Scaling Reinforcement Learning (RL) has the potential to enhance model performance beyond conventional pretraining and post-training methods.
Reinforcement Learning, Machine Learning, Generative AI
480 points by nwjsmith 27 days ago | 169 comments
RoboPianist: Dexterous Piano Playing with Deep Reinforcement Learning (2023) (kzakka.com)
We train anthropomorphic robot hands to play the piano using deep RL and release a simulated benchmark and dataset to advance high-dimensional control.
Robotics, Reinforcement Learning, Music, Artificial Intelligence, Machine Learning
142 points by bemmu 34 days ago | 53 comments
Competitive Programming with Large Reasoning Models (arxiv.org)
We show that reinforcement learning applied to large language models (LLMs) significantly boosts performance on complex coding and reasoning tasks.
Competitive Programming, Reinforcement Learning, Artificial Intelligence
16 points by t55 49 days ago | 1 comments
DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Scaling RL (notion.site)
DeepScaleR is an open-source project to fully democratize reinforcement learning (RL) for LLMs and reproduce DeepSeek R1 and OpenAI O1/O3 at scale on real tasks.
Reinforcement Learning, Open Source
322 points by sijuntan 49 days ago | 127 comments
DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Scaling RL (notion.site)
Deep Learning, Reinforcement Learning
19 points by mluo 50 days ago | 0 comments
Craftax: (Crafter and NetHack) RL Environment in Jax (github.com/MichaelTMatthews)
Craftax is an RL environment written entirely in JAX. Craftax reimplements and significantly extends the game mechanics of Crafter, taking inspiration from roguelike games such as NetHack.
Reinforcement Learning, Game Development, Python, Jax
14 points by lnyan 51 days ago | 2 comments
The Differences Between Direct Alignment Algorithms Are a Blur (arxiv.org)
Direct Alignment Algorithms (DAAs) simplify language model alignment by replacing reinforcement learning (RL) and reward modeling (RM) in Reinforcement Learning from Human Feedback (RLHF) with direct policy optimization.
Reinforcement Learning, Artificial Intelligence, Machine Learning
8 points by t55 51 days ago | 0 comments
There may not be aha moment in R1-Zero-like training (notion.site)
Machine Learning, Artificial Intelligence, Reinforcement Learning
78 points by qianli_cs 54 days ago | 8 comments
R1 Computer Use (github.com/agentsea)
r1-computer-use is an experimental project that applies large-scale Reinforcement Learning techniques similar to DeepSeek-R1 to computer usage scenarios.
Reinforcement Learning, Machine Learning, Experimental Projects, Computer Science
104 points by mountainriver 54 days ago | 57 comments
OSS reinforcement learning lib by ByteDance is used to reproduce DeepSeek R1 (github.com/volcengine)
verl is a flexible, efficient and production-ready RL training library for large language models (LLMs).
Reinforcement Learning, Open Source, ByteDance, AI
4 points by haibinlin 54 days ago | 1 comments
Deep Reinforcement Learning: Pong from Pixels (2016) (karpathy.github.io)
This is a long overdue blog post on Reinforcement Learning (RL). RL is hot! You may have noticed that computers can now automatically learn to play ATARI games (from raw game pixels!), they are beating world champions at Go, simulated quadrupeds are learning to run and leap, and robots are learning how to perform complex manipulation tasks that defy explicit programming.
Reinforcement Learning, Artificial Intelligence, Gaming, Machine Learning
111 points by Anon84 55 days ago | 6 comments
AMD Announces Open-Source "Schola" Library for Reinforcement Learning (phoronix.com)
AMD announced today the release of Schola 1.0 as an open-source reinforcement learning library that is being made available under an MIT license and as part of their GPUOpen software collection for helping game developers.
AMD, Open Source, Reinforcement Learning, Machine Learning
5 points by mindcrime 55 days ago | 0 comments
Reinforcement Learning: An Overview (arxiv.org)
This manuscript gives a big-picture, up-to-date overview of the field of (deep) reinforcement learning and sequential decision making, covering value-based RL, policy-gradient methods, model-based methods, and various other topics (including a very brief discussion of RL+LLMs).
Reinforcement Learning, Artificial Intelligence, Machine Learning
82 points by t55 58 days ago | 12 comments
RLHF Book (rlhfbook.com)
Reinforcement learning from human feedback (RLHF) has become an important technical and storytelling tool to deploy the latest machine learning systems.
Machine Learning, Artificial Intelligence, Reinforcement Learning
479 points by jxmorris12 59 days ago | 37 comments
Reinforcement Learning – A Reference (jakubhalmes.substack.com)
This text draws primarily from course materials for PA230 Reinforcement Learning, taught by Petr Novotný. Any errors or inaccuracies are my own.
Reinforcement Learning, Machine Learning, Education
108 points by jac08h 64 days ago | 3 comments
Emerging reasoning with reinforcement learning (notion.site)
Reinforcement Learning, Artificial Intelligence, Machine Learning
248 points by pella 66 days ago | 212 comments
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL (arxiv.org)
We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrates remarkable reasoning capabilities.
Generative AI, Reinforcement Learning, Artificial Intelligence, Machine Learning
1351 points by gradus_ad 66 days ago | 1056 comments
Kimi K1.5: Scaling Reinforcement Learning with LLMs (github.com/MoonshotAI)
🚀 Introducing Kimi k1.5 --- an o1-level multi-modal model
Reinforcement Learning, Artificial Intelligence, Open Source
203 points by noch 71 days ago | 29 comments
DeepSeek-R1-Distill-Qwen-1.5B Surpasses GPT-4o in certain benchmarks (huggingface.co)
We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning.
Generative AI, Benchmarking, Reinforcement Learning
39 points by BUFU 71 days ago | 17 comments