Infrastructure page 65

OpenAI News December 13, 2019 08:00

Dota 2 with large scale deep reinforcement learning

On April 13th, 2019, OpenAI Five became the first AI system to defeat the world champions at an esports game. The game of Dota 2 presents novel challenges for AI systems such as long time horizons, imperfect information, and complex, continuous state-action...

Topics: Models Infrastructure

Entities: OpenAI Models Infrastructure

OpenAI News December 05, 2019 08:00

Deep double descent

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...

Topics: Infrastructure

Entities: Infrastructure

OpenAI News November 21, 2019 08:00

Safety Gym

We’re releasing Safety Gym, a suite of environments and tools for measuring progress towards reinforcement learning agents that respect safety constraints while training.

Topics: Agents Infrastructure

Entities: Agents Infrastructure

OpenAI News November 21, 2019 08:00

Benchmarking safe exploration in deep reinforcement learning

Reinforcement learning (RL) agents need to explore their environments in order to learn optimal policies by trial and error. In many environments, safety is a critical concern and certain errors are unacceptable: for example, robotics systems that interact...

Topics: Agents Infrastructure

Entities: Agents Infrastructure

OpenAI News October 15, 2019 07:00

Solving Rubik’s Cube with a robot hand

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...

Topics: Models Infrastructure

Entities: OpenAI Models Infrastructure

OpenAI News September 17, 2019 07:00

Emergent tool use from multi-agent interaction

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...

Topics: Agents Infrastructure

Entities: Agents Infrastructure

OpenAI News August 22, 2019 07:00

Testing robustness against unforeseen adversaries

We’ve developed a method to assess whether a neural network classifier can reliably defend against adversarial attacks not seen during training. Our method yields a new metric, UAR (Unforeseen Attack Robustness), which evaluates the robustness of a single...

Topics: Infrastructure

Entities: Infrastructure

OpenAI News March 21, 2019 07:00

Implicit generation and generalization methods for energy-based models

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...

Topics: Models Infrastructure

Entities: Models Infrastructure

OpenAI News February 14, 2019 08:00

Better language models and their implications

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...

Topics: Models Infrastructure

Entities: Models Infrastructure

OpenAI News December 14, 2018 08:00

How AI training scales

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...

Topics: Infrastructure

Entities: Infrastructure

OpenAI News December 06, 2018 08:00

Quantifying generalization in reinforcement learning

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...

Topics: Infrastructure

Entities: Infrastructure

OpenAI News October 02, 2018 07:00

FFJORD: Free-form continuous dynamics for scalable reversible generative models

A promising class of generative models maps points from a simple distribution to a complex distribution through an invertible neural network. Likelihood-based training of these models requires restricting their architectures to allow cheap computation of...

Topics: Models Infrastructure

Entities: Models Infrastructure