Business
Gotta Learn Fast: A new benchmark for generalization in RL
Gotta Learn Fast: A new benchmark for generalization in RL.
OpenAI Blog · 104mo ago
4 min AI News & Insights
Older items first published newest-to-oldest across the feed — page 121 of 123.
Business
Retro Contest
We’re launching a transfer learning contest that measures a reinforcement learning algorithm’s ability to generalize from previous experience.
OpenAI Blog · 104mo ago
4 min 
Business
Variance reduction for policy gradient with action-dependent factorized baselines
Variance reduction for policy gradient with action-dependent factorized baselines.
OpenAI Blog · 104mo ago
4 min 
Business
Report from the OpenAI hackathon
On March 3rd, we hosted our first hackathon with 100 members of the artificial intelligence community.
#openai
OpenAI Blog · 104mo ago
4 min 
Business
Improving GANs using optimal transport
Improving GANs using optimal transport.
OpenAI Blog · 104mo ago
4 min 
Business
On first-order meta-learning algorithms
On first-order meta-learning algorithms.
#meta
OpenAI Blog · 105mo ago
4 min 
Business
Reptile: A scalable meta-learning algorithm
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...
#meta
OpenAI Blog · 105mo ago
4 min 
Business
OpenAI Scholars
We’re providing 6–10 stipends and mentorship to individuals from underrepresented groups to study deep learning full-time for 3 months and open-source a project.
#openai
#open-source
OpenAI Blog · 105mo ago
4 min 
Business
Some considerations on learning to explore via meta-reinforcement learning
Some considerations on learning to explore via meta-reinforcement learning.
#meta
OpenAI Blog · 105mo ago
4 min 
Business
Ingredients for robotics research
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...
OpenAI Blog · 105mo ago
4 min 
Business
Multi-Goal Reinforcement Learning: Challenging robotics environments and request for research
Multi-Goal Reinforcement Learning: Challenging robotics environments and request for research.
OpenAI Blog · 105mo ago
4 min 
Business
OpenAI hackathon
Come to OpenAI’s office in San Francisco’s Mission District for talks and a hackathon on Saturday, March 3rd.
#openai
OpenAI Blog · 105mo ago
4 min 
Business
Business
Preparing for malicious uses of AI
We’ve co-authored a paper that forecasts how malicious actors could misuse AI technology, and potential ways we can prevent and mitigate these threats. This paper is the outcome of almost a year...
OpenAI Blog · 105mo ago
4 min 
Business
Interpretable machine learning through teaching
We’ve designed a method that encourages AIs to teach each other with examples that also make sense to humans.
OpenAI Blog · 105mo ago
4 min 
Business
Discovering types for entity disambiguation
We’ve built a system for automatically figuring out which object is meant by a word by having a neural network decide if the word belongs to each of about 100 automatically-discovered “types”...
OpenAI Blog · 106mo ago
4 min 
Business
Requests for Research 2.0
We’re releasing a new batch of seven unsolved problems which have come up in the course of our research at OpenAI.
#openai
OpenAI Blog · 106mo ago
4 min 
Business
Business
Block-sparse GPU kernels
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...
OpenAI Blog · 108mo ago
4 min 
Business
Learning sparse neural networks through L₀ regularization
Learning sparse neural networks through L₀ regularization.
OpenAI Blog · 108mo ago
4 min 
Business
Interpretable and pedagogical examples
Interpretable and pedagogical examples.
OpenAI Blog · 109mo ago
4 min 
Business
Learning a hierarchy
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....
OpenAI Blog · 109mo ago
4 min 
Business
Generalizing from simulation
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....
OpenAI Blog · 109mo ago
4 min 
Business
Sim-to-real transfer of robotic control with dynamics randomization
Sim-to-real transfer of robotic control with dynamics randomization.
OpenAI Blog · 109mo ago
4 min 
Business
Asymmetric actor critic for image-based robot learning
Asymmetric actor critic for image-based robot learning.
OpenAI Blog · 109mo ago
4 min 
Business
Domain randomization and generative models for robotic grasping
Domain randomization and generative models for robotic grasping.
OpenAI Blog · 109mo ago
4 min 
Business
Competitive self-play
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...
OpenAI Blog · 110mo ago
4 min 
Business
Meta-learning for wrestling
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...
#meta
#agent
OpenAI Blog · 110mo ago
4 min 
Business
Nonlinear computation in deep linear networks
Nonlinear computation in deep linear networks.
OpenAI Blog · 110mo ago
4 min 
Business
Learning to model other minds
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...
#agent
OpenAI Blog · 111mo ago
4 min