Hacker News with Generative AI: Reinforcement Learning

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 9 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 9 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 10 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 10 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 11 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 14 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 14 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 14 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 15 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 15 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 18 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 19 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 23 days ago | 3 comments
Emerging reasoning with reinforcement learning (notion.site)
Reinforcement Learning, Artificial Intelligence, Machine Learning
248 points by pella 26 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 26 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 30 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 31 days ago | 17 comments
A path to O1 open source (arxiv.org)
OpenAI o1 represents a significant milestone in Artificial Inteiligence, which achieves expert-level performances on many challanging tasks that require strong reasoning this http URL has claimed that the main techinique behinds o1 is the reinforcement learining.
Artificial Intelligence, Open Source, Reinforcement Learning
133 points by bchelli 48 days ago | 80 comments
Offline Reinforcement Learning for LLM Multi-Step Reasoning (arxiv.org)
Improving the multi-step reasoning ability of large language models (LLMs) with offline reinforcement learning (RL) is essential for quickly adapting them to complex tasks.
Reinforcement Learning, Artificial Intelligence
111 points by belter 59 days ago | 9 comments
Puffer.ai – Simplifying reinforcement learning for complex game environments (puffer.ai)
PufferLib is the reinforcement learning library I wish existed during my PhD. It started as a compatibility layer to make working with complex environments a breeze. Now, it's a high-performance toolkit for research and industry with optimized parallel simulation, environments that run and train at 1M+ steps/second, and tons of quality of life improvements for practitioners. All our tools are free and open source. We also offer priority service for companies, startups, and labs!
Reinforcement Learning, Artificial Intelligence, Open Source, Game Development, Research
9 points by marcin_konow 67 days ago | 0 comments
Decisions and Dragons (decisionsanddragons.com)
A guide to the perilous world of reinforcement learning.
Reinforcement Learning, Machine Learning, Artificial Intelligence, Computer Science
6 points by todsacerdoti 93 days ago | 0 comments
Batched reward model inference and Best-of-N sampling (raw.sh)
Reward models have been a key part of reinforcement learning on top of LLMs, used broadly in techniques like RLHF and as LLM-as-a-judge critics in evals.
Reinforcement Learning, Artificial Intelligence, Machine Learning
34 points by rawsh 94 days ago | 0 comments
Reinforcement Learning – My Algorithm vs. State of the Art [video] (youtube.com)
Reinforcement Learning, Machine Learning, Artificial Intelligence, Video
6 points by sandebert 101 days ago | 0 comments
Show HN: RL Agent that can auto-optimize your LLM prompts (nomadic-ml.github.io)
The RL Prompt Optimizer employs a reinforcement learning framework to iteratively improve prompts used for language model evaluations.
Reinforcement Learning, Machine Learning, Prompt Engineering
14 points by varunkrishnan17 104 days ago | 2 comments
WebRL: Training LLM Web Agents via Self-Evolving Online Reinforcement Learning (arxiv.org)
Large language models (LLMs) have shown remarkable potential as autonomous agents, particularly in web-based tasks.
Artificial Intelligence, Reinforcement Learning, Web Development
23 points by theredsix 107 days ago | 1 comments
Using reinforcement learning and $4.80 of GPU time to find the best HN post (openpipe.ai)
Using Reinforcement Learning and $4.80 of GPU Time to Find the Best HN Post Ever (RLHF Part 1)
Reinforcement Learning, Artificial Intelligence, Hacker News, Machine Learning
217 points by kcorbitt 115 days ago | 95 comments
Reinforcement Learning: An Introduction (2018) (incompleteideas.net)
Reinforcement Learning, Machine Learning, Artificial Intelligence, Computer Science, Education
120 points by ibobev 121 days ago | 23 comments
Supporting Task Switching with Reinforcement Learning (dl.acm.org)
Human attention is a limited resource, but it is stressed more than ever before in history [2, 81].
Reinforcement Learning, Human-Computer Interaction, Artificial Intelligence
20 points by Topfi 125 days ago | 0 comments
Diffusion for World Modeling (diamond-wm.github.io)
DIAMOND 💎 (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained entirely in a diffusion world model. The agent playing in the diffusion model is shown above.
Reinforcement Learning, World Modeling, Generative AI
476 points by francoisfleuret 130 days ago | 218 comments
Training Language Models to Self-Correct via Reinforcement Learning (arxiv.org)
Self-correction is a highly desirable capability of large language models (LLMs), yet it has consistently been found to be largely ineffective in modern LLMs.
Generative AI, Reinforcement Learning, Machine Learning
230 points by weirdcat 153 days ago | 92 comments