~/devreads

#research

216 posts

4 Jun

3 Jun

28 May

Katie Washabaugh 7 min read

Robotics is entering a new phase: moving from controlled demos and scripted automation toward generalizable, reliable embodied autonomy in the real world. At the International Conference on Robotics and Automation (ICRA), eight of NVIDIA Research’s 28 accepted papers show how simulation-to-real transfer is becoming a foundation for that shift, helping robots perceive, reason, plan and […]

researchroboticsisaacnvidia researchomniverse

Criteo Tech 13 min read

Authors: Ahmed Ben Yahmed , Antoine Schnepf , Karim Kassab , and Mélissa Tamine . The 14th International Conference on Learning Representations ( ICLR 2026 ) was held from April 23 to 27, 2026, at the Riocentro Convention and Event Center in Rio de Janeiro, Brazil. It was the first time the conference made its way to South America. As…

iclrllmresearchagentic-aiai

20 May

12 May

7 May

Brian Caulfield 4 min read

AI will help build the energy it needs. That’s the case U.S. Energy Secretary Chris Wright and NVIDIA Vice President of Hyperscale and High-Performance Computing Ian Buck made Thursday morning at the SCSP AI+ Expo. The 30-minute fireside chat, moderated by SCSP president Ylli Bajraktari, was called “Powering the Next American Century.” Their argument: American […]

ai infrastructurecorporatehardwareresearchsupercomputing

30 Apr

Criteo Tech 8 min read

Author: Alain Rakotomamonjy From ideation to outcome, this is the story of a privacy-preserving research project. It tells how research can generate innovations but also joy and despair. Early 2024: The “Hammer” Phase Two research leads who pioneered Criteo’s early privacy initiatives, as part of the Criteo multi-year research program, introduced me to a challenge born from the Privacy Sandbox…

research-paperpaperresearchalgorithmsscience

23 Apr

22 Apr

16 Apr

7 Apr

João Bernardo Narciso 8 min read

Uncovering the Shape of Fraud with Cosmos Explorer: Visual Metaphors Behind Millions of Transactions The Data Visualization Research team is developing Cosmos Explorer, an interface that leverages universe-related visual metaphors to convey information about the billions of transactions processed by Feedzai. Pedro Cruz, professor at Northeastern University, partnered with Feedzai to bring this idea to life by contributing with his…

datavizfrauddesignresearchfraud-detection

25 Mar

12 Mar

Yiwen Xu 3 min read

Building agents is now a strategic priority for 95% of respondents in our latest State of Agentic AI research, which surveyed more than 800 developers and decision-makers worldwide. The shift is happening quickly: agent adoption has moved beyond experiments and demos into early operational maturity. But the road to enterprise-scale adoption is still complex. The...

enterpriseresearchai mldocker

10 Mar

Yiwen Xu 3 min read

It’s hard to find a team today that isn’t talking about agents. For most organizations, this isn’t a “someday” project anymore. Building agents is a strategic priority for 95% of respondents that we surveyed across the globe with 800+ developers and decision makers in our latest State of Agentic AI research. The shift is happening...

enterpriseresearchai mldocker

5 Mar

4 Mar

23 Feb

20 Feb

Yiwen Xu 2 min read

Based on Docker’s State of Agentic AI report, a global survey of more than 800 developers, platform engineers, and technology decision-makers, this blog summarizes key findings of what's really happening as agentic AI scales within organizations. Drawing on insights from decision-makers and purchase influencers worldwide, we'll give you a preview on not only where teams...

researchai mldevelopersenterprise

18 Feb

1 min read

OpenAI and Paradigm introduce EVMbench, a benchmark evaluating AI agents’ ability to detect, patch, and exploit high-severity smart contract vulnerabilities.

research

13 Feb

5 Feb

8 Jan

Zoe Kessler 3 min read

The next universal technology since the smartphone is on the horizon — and it may be a little less pocket friendly. The Moonshot research program, funded by the Japan Science and Technology Agency and accelerated by NVIDIA AI and robotics technologies, is working to create a world by 2050 where AI-powered, autonomously learning robots are […]

researchroboticsai for goodgpuhealthcare and life sciences

22 Dec 2025

Zoe Kessler 4 min read

The works of Plato state that when humans have an experience, some level of change occurs in their brain, which is powered by memory — specifically long-term memory. This change is what Andre Fenton, professor of neural science at New York University, and Abhishek Kumar, assistant professor of cell and regenerative biology at the University […]

airesearchworkstationeducationnvidia rtx

18 Dec 2025

1 min read

OpenAI introduces a new framework and evaluation suite for chain-of-thought monitorability, covering 13 evaluations across 24 environments. Our findings show that monitoring a model’s internal reasoning is far more effective than monitoring outputs alone, offering a promising path toward scalable control as AI systems grow more capable.

research

17 Dec 2025

Zoe Kessler 4 min read

The Hao AI Lab research team at the University of California San Diego — at the forefront of pioneering AI model innovation — recently received an NVIDIA DGX B200 system to elevate their critical work in large language model inference. Many LLM inference platforms in production today, such as NVIDIA Dynamo, use research concepts that […]

aiai infrastructureresearchsupercomputingartificial intelligence

16 Dec 2025

4 Dec 2025

Sylvia Chanak 2 min read

For 25 years, the NVIDIA Graduate Fellowship Program has supported graduate students doing outstanding work relevant to NVIDIA technologies. Today, the program announced the latest awards of up to $60,000 each to 10 Ph.D. students involved in research that spans all areas of computing innovation. Selected from a highly competitive applicant pool, the awardees will […]

airesearchartificial intelligenceeducation

3 Dec 2025

1 Dec 2025

Bryan Catanzaro 6 min read

Researchers worldwide rely on open-source technologies as the foundation of their work. To equip the community with the latest advancements in digital and physical AI, NVIDIA is further expanding its collection of open AI models, datasets and tools — with potential applications in virtually every research field. At NeurIPS, one of the world’s top AI […]

aicorporatedrivingresearchrobotics

20 Nov 2025

Zoe Kessler 4 min read

Tanya Berger-Wolf’s first computational biology project started as a bet with a colleague: that she could build an AI model capable of identifying individual zebras faster than a zoologist. She won. Now, the director of the Translational Data Analytics Institute and a professor at The Ohio State University, Berger-Wolf is taking on the whole animal […]

airesearchartificial intelligenceeducationscience

19 Nov 2025

18 Nov 2025

17 Nov 2025

Kibibi Moseley 5 min read

To power future technologies including liquid-cooled data centers, high-resolution digital displays and long-lasting batteries, scientists are searching for novel chemicals and materials optimized for factors like energy use, durability and efficacy. New NVIDIA-accelerated data processing pipelines and AI microservices unveiled at the SC25 conference in St. Louis are advancing chemistry and material science to support […]

ai infrastructureresearchsupercomputingartificial intelligencecuda-x

13 Nov 2025

3 Nov 2025

1 min read

OpenAI introduces IndQA, a new benchmark for evaluating AI systems in Indian languages. Built with domain experts, IndQA tests cultural understanding and reasoning across 12 languages and 10 knowledge areas.

research

9 Oct 2025

3 Oct 2025

Jacopo Bono 12 min read

Introduction Over the years, we have evolved from using simple, often rule-based algorithms to sophisticated machine learning models. These models are incredibly good at finding patterns in large datasets, but due to their complexity it is frequently challenging for a human to understand why a certain input leads to its respective output. This is especially problematic in areas where high-stakes…

researchconcept-learningcausalitydeep-learningexplainability

30 Sept 2025

1 min read

Our latest video generation model is more physically accurate, realistic, and controllable than prior systems. It also features synchronized dialogue and sound effects. Create with it in the new Sora app.

research

15 Sept 2025

1 min read

New research from the largest study of ChatGPT use shows how the tool creates economic value through both personal and professional use. Adoption is broadening beyond early users, closing gaps and making AI a part of everyday life.

research

5 Sept 2025

25 Jul 2025

Sofia Guerreiro 8 min read

By Sofia Guerreiro, Ricardo Ribeiro Pereira, Iker Perez, Jacopo Bono Detecting financial fraud is like finding a moving needle in a shifting haystack . Fraud accounts for a tiny fraction of financial transactions, often less than 0.1%. At the same time, fraudsters are constantly adapting their tactics to evade detection. And this happens within a live and dynamic environment, where…

machine-learningfraud-detectionresearchnetwork-intelligencefeedzai

21 Mar 2025

2 Feb 2025

1 min read

An agent that uses reasoning to synthesize large amounts of online information and complete multi-step research tasks for you. Available to Pro users today, Plus and Team next.

research

31 Jan 2025

23 Jan 2025

22 Jan 2025

5 Dec 2024

1 min read

This report outlines the safety work carried out prior to releasing OpenAI o1 and o1-mini, including external red teaming and frontier risk evaluations according to our Preparedness Framework.

research

22 Nov 2024

Beatriz Feliciano 4 min read

Every year, millions of people fall victim to financial fraud. In 2023, the losses tied to this type of crime were estimated at US$159 billion just in the US , with some people losing all of their retirement savings to scammers . However, the impacts of this issue stretch beyond someone’s finances. It can also impact a victim’s life in…

fraud-investigationresearchfinancial-frauddata-visualizationdata-analysis

21 Nov 2024

30 Oct 2024

23 Oct 2024

15 Oct 2024

10 Oct 2024

4 Oct 2024

Ricardo Ribeiro Pereira 9 min read

Digital systems have become deeply integrated into many aspects of modern life, particularly within the financial sector. While digital banking simplifies day-to-day operations for clients, it also creates new opportunities for malicious actors to exploit these systems. As a result, money laundering has grown particularly prevalent due to this digital expansion. Banks are required to monitor for money laundering activities…

gansmoney-launderingfeedzaigenairesearch

12 Sept 2024

13 Aug 2024

12 Aug 2024

Sérgio Jesus 9 min read

By Sérgio Jesus, Inês Silva, Pedro Saleiro, Hugo Ferreira, Pedro Bizarro In this blog post we will visit Aequitas Flow , an Open-Source framework designed to run complete and standardized experiments of Fair ML algorithms. We encourage you to try Aequitas Flow with the Google Colab Notebooks, which are available in the project’s GitHub repository . This blog post is…

responsible-aifairnessopen-sourceresearchmachine-learning

24 Jul 2024

18 Jul 2024

17 Jul 2024

10 Jul 2024

21 Jun 2024

Javier Liébana 13 min read

In the world of financial services, the bank or financial institution’s relationship with the customer relies on digital trust , which is anchored in two fundamental principles. First, it must ensure the person engaging through digital banking channels is genuinely the individual they claim to be. Second, it must confirm that this person is authorized to complete the intended financial…

feedzaidigital-trustonline-fraud-preventionmachine-learningresearch

20 Jun 2024

1 min read

Diffusion models have significantly advanced the fields of image, audio, and video generation, but they depend on an iterative sampling process that causes slow generation.

research

6 Jun 2024

13 May 2024

7 May 2024

19 Apr 2024

15 Feb 2024

1 min read

We explore large-scale training of generative models on video data. Specifically, we train text-conditional diffusion models jointly on videos and images of variable durations, resolutions and aspect ratios. We leverage a transformer architecture that operates on spacetime patches of video and image latent codes. Our largest model, Sora, is capable of generating a minute of high fidelity video. Our results…

research

31 Jan 2024

1 min read

We’re developing a blueprint for evaluating the risk that a large language model (LLM) could aid someone in creating a biological threat. In an evaluation involving both biology experts and students, we found that GPT-4 provides at most a mild uplift in biological threat creation accuracy. While this uplift is not large enough to be conclusive, our finding is a…

research

31 May 2023

1 min read

We've trained a model to achieve a new state-of-the-art in mathematical problem solving by rewarding each correct step of reasoning (“process supervision”) instead of simply rewarding the correct final answer (“outcome supervision”). In addition to boosting performance relative to outcome supervision, process supervision also has an important alignment benefit: it directly trains the model to produce a chain-of-thought that is…

research

25 May 2023

1 min read

Our nonprofit organization, OpenAI, Inc., is launching a program to award ten $100,000 grants to fund experiments in setting up a democratic process for deciding what rules AI systems should follow, within the bounds defined by the law.

research

17 Mar 2023

14 Mar 2023

1 min read

We’ve created GPT-4, the latest milestone in OpenAI’s effort in scaling up deep learning. GPT-4 is a large multimodal model (accepting image and text inputs, emitting text outputs) that, while less capable than humans in many real-world scenarios, exhibits human-level performance on various professional and academic benchmarks.

research

16 Dec 2022

19 Oct 2022

21 Sept 2022

28 Jul 2022

28 Jun 2022

1 min read

In order to share the magic of DALL·E 2 with a broad audience, we needed to reduce the risks associated with powerful image generation models. To this end, we put various guardrails in place to prevent generated images from violating our content policy.

research

23 Jun 2022

1 min read

We trained a neural network to play Minecraft by Video PreTraining (VPT) on a massive unlabeled video dataset of human Minecraft play, while using only a small amount of labeled contractor data. With fine-tuning, our model can learn to craft diamond tools, a task that usually takes proficient humans over 20 minutes (24,000 actions). Our model uses the native human…

research

17 Jun 2022

9 Jun 2022

28 May 2022

13 Apr 2022

3 Mar 2022

2 Feb 2022

24 Jan 2022

16 Dec 2021

29 Oct 2021

1 min read

We’ve trained a system that solves grade school math problems with nearly twice the accuracy of a fine-tuned GPT-3 model. It solves about 90% as many problems as real kids: a small sample of 9-12 year olds scored 60% on a test from our dataset, while our system scored 55% on those same problems.

research

8 Sept 2021

28 Jul 2021

7 Jul 2021

1 Jul 2021

Ken Howard 1 min read

Cloud-based applications have helped make a new world of work possible. But they have also opened up the doors to new risks and threats, such as ransomware by remote desktop takeover and data loss through unprotected cloud storage use. The post Cloud Application Security – Risks, Questions, Insights, and Solutions appeared first on Cisco Umbrella.

research

4 Mar 2021

1 min read

We’ve discovered neurons in CLIP that respond to the same concept whether presented literally, symbolically, or conceptually. This may explain CLIP’s accuracy in classifying surprising visual renditions of concepts, and is also an important step toward understanding the associations and biases that CLIP and similar models learn.

research

4 Feb 2021

25 Jan 2021

1 min read

We’ve scaled Kubernetes clusters to 7,500 nodes, producing a scalable infrastructure for large models like GPT-3, CLIP, and DALL·E, but also for rapid small-scale iterative research such as Scaling Laws for Neural Language Models.

research

5 Jan 2021

1 min read

We’re introducing a neural network called CLIP which efficiently learns visual concepts from natural language supervision. CLIP can be applied to any visual classification benchmark by simply providing the names of the visual categories to be recognized, similar to the “zero-shot” capabilities of GPT-2 and GPT-3.

research

7 Sept 2020

17 Jun 2020

1 min read

We find that, just as a large transformer model trained on language can generate coherent text, the same exact model trained on pixel sequences can generate coherent image completions and samples. By establishing a correlation between sample quality and image classification accuracy, we show that our best generative model also contains features competitive with top convolutional nets in the unsupervised…

research

28 May 2020

5 May 2020

1 min read

We’re releasing an analysis showing that since 2012 the amount of compute needed to train a neural net to the same performance on ImageNet classification has been decreasing by a factor of 2 every 16 months. Compared to 2012, it now takes 44 times less compute to train a neural network to the level of AlexNet (by contrast, Moore’s Law…

research

30 Apr 2020

1 min read

We’re introducing Jukebox, a neural net that generates music, including rudimentary singing, as raw audio in a variety of genres and artist styles. We’re releasing the model weights and code, along with a tool to explore the generated samples.

research

16 Apr 2020

1 min read

We’ve contributed to a multi-stakeholder report by 58 co-authors at 30 organizations, including the Centre for the Future of Intelligence, Mila, Schwartz Reisman Institute for Technology and Society, Center for Advanced Study in the Behavioral Sciences, and Center for Security and Emerging Technologies. This report describes 10 mechanisms to improve the verifiability of claims made about AI systems. Developers can…

research

14 Apr 2020

1 min read

We’re introducing OpenAI Microscope, a collection of visualizations of every significant layer and neuron of eight vision “model organisms” which are often studied in interpretability. Microscope makes it easier to analyze the features that form inside these neural networks, and we hope it will help the research community as we move towards understanding these complicated systems.

research

23 Jan 2020

19 Dec 2019

Kadir Topal 2 min read

The first annual MDN Developer Needs Assessment aims to represent the voices of developers and designers working on the web. We've analyzed the data provided by more than 28,000 completed surveys, and we've identified 28 discrete needs, sorted into 14 different themes. Four of the top ten needs relate to browser compatibility, our #1 theme. Documentation, Testing, Debugging, and Frameworks…

featured articlemdnnewsresearchsurvey

13 Dec 2019

5 Dec 2019

1 min read

We show that the double descent phenomenon occurs in CNNs, ResNets, and transformers: performance first improves, then gets worse, and then improves again with increasing model size, data size, or training time. This effect is often avoided through careful regularization. While this behavior appears to be fairly universal, we don’t yet fully understand why it happens, and view further study…

research

3 Dec 2019

1 min read

We’re releasing Procgen Benchmark, 16 simple-to-use procedurally-generated environments which provide a direct measure of how quickly a reinforcement learning agent learns generalizable skills.

research

5 Nov 2019

1 min read

As the final model release of GPT-2’s staged release, we’re releasing the largest version (1.5B parameters) of GPT-2 along with code and model weights to facilitate detection of outputs of GPT-2 models. While there have been larger language models released since August, we’ve continued with our original staged release plan in order to provide the community with a test case…

research

15 Oct 2019

1 min read

We’ve trained a pair of neural networks to solve the Rubik’s Cube with a human-like robot hand. The neural networks are trained entirely in simulation, using the same reinforcement learning code as OpenAI Five paired with a new technique called Automatic Domain Randomization (ADR). The system can handle situations it never saw during training, such as being prodded by a…

research

17 Sept 2019

1 min read

We’ve observed agents discovering progressively more complex tool use while playing a simple game of hide-and-seek. Through training in our new simulated hide-and-seek environment, agents build a series of six distinct strategies and counterstrategies, some of which we did not know our environment supported. The self-supervised emergent complexity in this simple environment further suggests that multi-agent co-adaptation may one day…

research

20 Aug 2019

1 min read

We’re releasing the 774 million parameter GPT-2 language model after the release of our small 124M model in February, staged release of our medium 355M model in May, and subsequent research with partners and the AI community into the model’s potential for misuse and societal benefit. We’re also releasing an open-source legal agreement to make it easier for organizations to…

research

23 May 2019

Nathan Egge 3 min read

With this week's release of Firefox 67, the new high performance royalty-free AV1 video decoder dav1d is now enabled by default on all desktop platforms (Windows, OSX and Linux) for both 32-bit and 64-bit systems. And work is in progress on rav1e, the Rust AV1 encoder. The post Firefox brings you smooth video playback with the world’s fastest AV1 decoder…

av1featured articlefirefoxperformanceresearch

25 Apr 2019

1 min read

We’ve created MuseNet, a deep neural network that can generate 4-minute musical compositions with 10 different instruments, and can combine styles from country to Mozart to the Beatles. MuseNet was not explicitly programmed with our understanding of music, but instead discovered patterns of harmony, rhythm, and style by learning to predict the next token in hundreds of thousands of MIDI…

research

23 Apr 2019

1 min read

We’ve developed the Sparse Transformer, a deep neural network which sets new records at predicting what comes next in a sequence—whether text, images, or sound. It uses an algorithmic improvement of the attention mechanism to extract patterns from sequences 30x longer than possible previously.

research

15 Apr 2019

1 min read

OpenAI Five is the first AI to beat the world champions in an esports game, having won two back-to-back games versus the world champion Dota 2 team, OG, at Finals this weekend. Both OpenAI Five and DeepMind’s AlphaStar had previously beaten good pros privately but lost their live pro matches, making this also the first time an AI has beaten…

research

21 Mar 2019

1 min read

We’ve made progress towards stable and scalable training of energy-based models (EBMs) resulting in better sample quality and generalization ability than existing models. Generation in EBMs spends more compute to continually refine its answers and doing so can generate samples competitive with GANs at low temperatures, while also having mode coverage guarantees of likelihood-based models. We hope these findings stimulate…

research

4 Mar 2019

1 min read

We’re releasing a Neural MMO, a massively multiagent game environment for reinforcement learning agents. Our platform supports a large, variable number of agents within a persistent and open-ended task. The inclusion of many agents and species leads to better exploration, divergent niche formation, and greater overall competence.

research

14 Feb 2019

1 min read

We’ve trained a large-scale unsupervised language model which generates coherent paragraphs of text, achieves state-of-the-art performance on many language modeling benchmarks, and performs rudimentary reading comprehension, machine translation, question answering, and summarization—all without task-specific training.

research

4 Feb 2019

14 Dec 2018

1 min read

We’ve discovered that the gradient noise scale, a simple statistical metric, predicts the parallelizability of neural network training on a wide range of tasks. Since complex tasks tend to have noisier gradients, increasingly large batch sizes are likely to become useful in the future, removing one potential limit to further growth of AI systems. More broadly, these results show that…

research

6 Dec 2018

1 min read

We’re releasing CoinRun, a training environment which provides a metric for an agent’s ability to transfer its experience to novel situations and has already helped clarify a longstanding puzzle in reinforcement learning. CoinRun strikes a desirable balance in complexity: the environment is simpler than traditional platformer games like Sonic the Hedgehog but still poses a worthy generalization challenge for state…

research

8 Nov 2018

1 min read

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.

research

7 Nov 2018

1 min read

We’ve developed an energy-based model that can quickly learn to identify and generate instances of concepts, such as near, above, between, closest, and furthest, expressed as sets of 2d points. Our model learns these concepts after only five demonstrations. We also show cross-domain transfer: we use concepts learned in a 2d particle environment to solve tasks on a 3-dimensional physics-based…

research

5 Nov 2018

31 Oct 2018

2 Oct 2018

23 Aug 2018

13 Aug 2018

6 Aug 2018

1 min read

Yesterday, OpenAI Five won a best-of-three against a team of 99.95th percentile Dota players: Blitz, Cap, Fogged, Merlini, and MoonMeander—four of whom have played Dota professionally—in front of a live audience and 100,000 concurrent livestream viewers.

research

30 Jul 2018

26 Jul 2018

9 Jul 2018

1 min read

We introduce Glow, a reversible generative model which uses invertible 1x1 convolutions. It extends previous work on reversible generative models and simplifies the architecture. Our model can generate realistic high resolution images, supports efficient sampling, and discovers features that can be used to manipulate attributes of data. We’re releasing code for the model and an online visualization tool so people…

research

4 Jul 2018

1 min read

We’ve trained an agent to achieve a high score of 74,500 on Montezuma’s Revenge from a single human demonstration, better than any previously published result. Our algorithm is simple: the agent plays a sequence of games starting from carefully chosen states from the demonstration, and learns from them by optimizing the game score using PPO, the same reinforcement learning algorithm…

research

25 Jun 2018

22 Jun 2018

17 Jun 2018

2 Jun 2018

25 May 2018

1 min read

We’re releasing the full version of Gym Retro, a platform for reinforcement learning research on games. This brings our publicly-released game count from around 70 Atari games and 30 Sega games to over 1,000 games across a variety of backing emulators. We’re also releasing the tool we use to add new games to the platform.

research

16 May 2018

1 min read

We’re releasing an analysis showing that since 2012, the amount of compute used in the largest AI training runs has been increasing exponentially with a 3.4-month doubling time (by comparison, Moore’s Law had a 2-year doubling period)[^footnote-correction]. Since 2012, this metric has grown by more than 300,000x (a 2-year doubling period would yield only a 7x increase). Improvements in compute…

research

18 Apr 2018

1 min read

We’re releasing an experimental metalearning approach called Evolved Policy Gradients, a method that evolves the loss function of learning agents, which can enable fast training on novel tasks. Agents trained with EPG can succeed at basic tasks at test time that were outside their training regime, like learning to navigate to an object on a different side of the room…

research

10 Apr 2018

5 Apr 2018

1 min read

We’re launching a transfer learning contest that measures a reinforcement learning algorithm’s ability to generalize from previous experience.

research

20 Mar 2018

15 Mar 2018

8 Mar 2018

7 Mar 2018

1 min read

We’ve developed a simple meta-learning algorithm called Reptile which works by repeatedly sampling a task, performing stochastic gradient descent on it, and updating the initial parameters towards the final parameters learned on that task. Reptile is the application of the Shortest Descent algorithm to the meta-learning setting, and is mathematically similar to first-order MAML (which is a version of the…

research

3 Mar 2018

26 Feb 2018

1 min read

We’re releasing eight simulated robotics environments and a Baselines implementation of Hindsight Experience Replay, all developed for our research over the past year. We’ve used these environments to train models which work on physical robots. We’re also releasing a set of requests for robotics research.

research

15 Feb 2018

1 min read

We’ve designed a method that encourages AIs to teach each other with examples that also make sense to humans. Our approach automatically selects the most informative examples to teach a concept—for instance, the best images to describe the concept of dogs—and experimentally we found our approach to be effective at teaching both AIs

research

7 Feb 2018

31 Jan 2018

18 Jan 2018

6 Dec 2017

1 min read

We’re releasing highly-optimized GPU kernels for an underexplored class of neural network architectures: networks with block-sparse weights. Depending on the chosen sparsity, these kernels can run orders of magnitude faster than cuBLAS or cuSPARSE. We’ve used them to attain state-of-the-art results in text sentiment analysis and generative modeling of text and images.

research

4 Dec 2017

2 Nov 2017

26 Oct 2017

1 min read

We’ve developed a hierarchical reinforcement learning algorithm that learns high-level actions useful for solving a range of tasks, allowing fast solving of tasks requiring thousands of timesteps. Our algorithm, when applied to a set of navigation problems, discovers a set of high-level actions for walking and crawling in different directions, which enables the agent to master new navigation tasks quickly.

research

19 Oct 2017

1 min read

Our latest robotics techniques allow robot controllers, trained entirely in simulation and deployed on physical robots, to react to unplanned changes in the environment as they solve simple tasks. That is, we’ve used these techniques to build closed-loop systems rather than open-loop ones as before.

research

18 Oct 2017

17 Oct 2017

11 Oct 2017

1 min read

We show that for the task of simulated robot wrestling, a meta-learning agent can learn to quickly defeat a stronger non-meta-learning agent, and also show that the meta-learning agent can adapt to physical malfunction.

research

1 min read

We’ve found that self-play allows simulated AIs to discover physical skills like tackling, ducking, faking, kicking, catching, and diving for the ball, without explicitly designing an environment with these skills in mind. Self-play ensures that the environment is always the right difficulty for an AI to improve. Taken alongside our Dota 2 self-play results, we have increasing confidence that self-play…

research

29 Sept 2017

14 Sept 2017

1 min read

We’re releasing an algorithm which accounts for the fact that other agents are learning too, and discovers self-interested yet collaborative strategies like tit-for-tat in the iterated prisoner’s dilemma. This algorithm, Learning with Opponent-Learning Awareness (LOLA), is a small step towards agents that model other minds.

research

13 Sept 2017

18 Aug 2017

1 min read

We’re releasing two new OpenAI Baselines implementations: ACKTR and A2C. A2C is a synchronous, deterministic variant of Asynchronous Advantage Actor Critic (A3C) which we’ve found gives equal performance. ACKTR is a more sample-efficient reinforcement learning algorithm than TRPO and A2C, and requires only slightly more computation than A2C per update.

research

16 Aug 2017

1 min read

Our Dota 2 result shows that self-play can catapult the performance of machine learning systems from far below human level to superhuman, given sufficient compute. In the span of a month, our system went from barely matching a high-ranked player to beating the top pros and has continued to improve since then. Supervised deep learning systems can only be as…

research

11 Aug 2017

1 min read

We’ve created a bot which beats the world’s top professionals at 1v1 matches of Dota 2 under standard tournament rules. The bot learned the game from scratch by self-play, and does not use imitation learning or tree search. This is a step towards building AI systems which accomplish well-defined goals in messy, complicated situations involving real humans.

research

3 Aug 2017

1 min read

RL-Teacher is an open-source implementation of our interface to train AIs via occasional human feedback rather than hand-crafted reward functions. The underlying technique was developed as a step towards safe AI systems, but also applies to reinforcement learning problems with rewards that are hard to specify.

research

27 Jul 2017

1 min read

We’ve found that adding adaptive noise to the parameters of reinforcement learning algorithms frequently boosts performance. This exploration method is simple to implement and very rarely decreases performance, so it’s worth trying on any problem.

research

20 Jul 2017

1 min read

We’re releasing a new class of reinforcement learning algorithms, Proximal Policy Optimization (PPO), which perform comparably or better than state-of-the-art approaches while being much simpler to implement and tune. PPO has become the default reinforcement learning algorithm at OpenAI because of its ease of use and good performance.

research

17 Jul 2017

1 min read

We’ve created images that reliably fool neural network classifiers when viewed from varied scales and perspectives. This challenges a claim from last week that self-driving cars would be hard to trick maliciously since they capture images from multiple scales, angles, perspectives, and the like.

research

5 Jul 2017

1 Jul 2017

28 Jun 2017

8 Jun 2017

1 min read

Multiagent environments where agents compete for resources are stepping stones on the path to AGI. Multiagent environments have two useful properties: first, there is a natural curriculum—the difficulty of the environment is determined by the skill of your competitors (and if you’re competing against clones of yourself, the environment exactly matches your skill level). Second, a multiagent environment has no…

research

5 Jun 2017

24 May 2017

1 min read

We’re open-sourcing OpenAI Baselines, our internal effort to reproduce reinforcement learning algorithms with performance on par with published results. We’ll release the algorithms over upcoming months; today’s release includes DQN and three of its variants.

research

16 May 2017

1 min read

We’ve created a robotics system, trained entirely in simulation and deployed on a physical robot, which can learn a new task after seeing it done once.

research

15 May 2017

21 Apr 2017

10 Apr 2017

6 Apr 2017

1 Apr 2017

24 Mar 2017

21 Mar 2017

16 Mar 2017

15 Mar 2017

12 Mar 2017

6 Mar 2017

19 Jan 2017

5 Dec 2016

1 min read

We’re releasing Universe, a software platform for measuring and training an AI’s general intelligence across the world’s supply of games, websites and other applications.

research

15 Nov 2016

14 Nov 2016

11 Nov 2016

9 Nov 2016

8 Nov 2016

2 Nov 2016

11 Oct 2016

29 Aug 2016

1 min read

Deep learning is an empirical science, and the quality of a group’s infrastructure is a multiplier on progress. Fortunately, today’s open-source ecosystem makes it possible for anyone to build great deep learning infrastructure.

research

16 Jun 2016

1 min read

This post describes four projects that share a common theme of enhancing or using generative models, a branch of unsupervised learning techniques in machine learning. In addition to describing our work, this post will tell you a bit more about generative models: what they are, why they are important, and where they might be going.

research

27 Apr 2016

1 min read

We’re releasing the public beta of OpenAI Gym, a toolkit for developing and comparing reinforcement learning (RL) algorithms. It consists of a growing suite of environments (from simulated robots to Atari games), and a site for comparing and reproducing results.

research

25 Feb 2016