OpenAI News
OpenAI Fellows Fall 2018
We’re now accepting applications for the next cohort of OpenAI Fellows, a program which offers a compensated 6-month apprenticeship in AI research at OpenAI.
Topics: Models
OpenAI News
Gym Retro
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....
OpenAI News
AI and compute
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]....
Topics: Infrastructure
Entities: Infrastructure
OpenAI News
AI safety via debate
We’re proposing an AI safety technique which trains agents to debate topics with one another, using a human to judge who wins.
OpenAI News
Evolved Policy Gradients
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...
Topics: AgentsPolicyInfrastructure
Entities: AgentsPolicyInfrastructure
OpenAI News
Gotta Learn Fast: A new benchmark for generalization in RL
In this report, we present a new reinforcement learning (RL) benchmark based on the Sonic the Hedgehog™ video game franchise. This benchmark is intended to measure the performance of transfer learning and few-shot learning algorithms in the RL domain. We...
OpenAI News
Retro Contest
We’re launching a transfer learning contest that measures a reinforcement learning algorithm’s ability to generalize from previous experience.
OpenAI News
Variance reduction for policy gradient with action-dependent factorized baselines
Policy gradient methods have enjoyed great success in deep reinforcement learning but suffer from high variance of gradient estimates. The high variance problem is particularly exasperated in problems with long horizons or high-dimensional action spaces. To...
Topics: Policy
OpenAI News
Report from the OpenAI hackathon
On March 3rd, we hosted our first hackathon with 100 members of the artificial intelligence community.
Topics: Models
OpenAI News
Improving GANs using optimal transport
We present Optimal Transport GAN (OT-GAN), a variant of generative adversarial nets minimizing a new metric measuring the distance between the generator distribution and the data distribution. This metric, which we call mini-batch energy distance, combines...
OpenAI News
On first-order meta-learning algorithms
This paper considers meta-learning problems, where there is a distribution of tasks, and we would like to obtain an agent that performs well (i.e., learns quickly) when presented with a previously unseen task sampled from this distribution. We analyze a...
Topics: Infrastructure
Entities: Infrastructure
OpenAI News
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 the final parameters learned on that task. Reptile is the...