Business
Learning with opponent-learning awareness
Learning with opponent-learning awareness.
OpenAI Blog · 111mo ago
4 min AI News & Insights
Older items first published newest-to-oldest across the feed — page 122 of 123.
Business
OpenAI Baselines: ACKTR & A2C
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...
#openai
OpenAI Blog · 111mo ago
4 min 
Business
More on Dota 2
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...
OpenAI Blog · 111mo ago
4 min 
Business
Dota 2
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...
OpenAI Blog · 112mo ago
4 min 
Business
Gathering human feedback
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...
#open-source
OpenAI Blog · 112mo ago
4 min 
Business
Better exploration with parameter noise
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...
OpenAI Blog · 112mo ago
4 min 
Business
Proximal Policy Optimization
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...
OpenAI Blog · 112mo ago
4 min 
Business
Robust adversarial inputs
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...
OpenAI Blog · 112mo ago
4 min 
Business
Business
Teacher–student curriculum learning
Teacher–student curriculum learning.
OpenAI Blog · 113mo ago
4 min 
Business
Faster physics in Python
We’re open-sourcing a high-performance Python library for robotic simulation using the MuJoCo engine, developed over our past year of robotics research.
OpenAI Blog · 113mo ago
4 min 
Business
Learning from human preferences
One step towards building safe AI systems is to remove the need for humans to write goal functions, since using a simple proxy for a complex goal, or getting the complex goal a bit wrong, can lead...
OpenAI Blog · 114mo ago
4 min 
Business
Learning to cooperate, compete, and communicate
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...
#agent
OpenAI Blog · 114mo ago
4 min 
Business
Business
OpenAI Baselines: DQN
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...
#openai
OpenAI Blog · 114mo ago
4 min 
Business
Robots that learn
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.
OpenAI Blog · 115mo ago
4 min 
Business
Roboschool
We are releasing Roboschool: open-source software for robot simulation, integrated with OpenAI Gym.
#openai
#open-source
OpenAI Blog · 115mo ago
4 min 
Business
Equivalence between policy gradients and soft Q-learning
Equivalence between policy gradients and soft Q-learning.
OpenAI Blog · 115mo ago
4 min 
Business
Stochastic Neural Networks for hierarchical reinforcement learning
Stochastic Neural Networks for hierarchical reinforcement learning.
OpenAI Blog · 116mo ago
4 min 
Business
Unsupervised sentiment neuron
We’ve developed an unsupervised system which learns an excellent representation of sentiment, despite being trained only to predict the next character in the text of Amazon reviews.
#amazon
OpenAI Blog · 116mo ago
4 min 
Business
Spam detection in the physical world
We’ve created the world’s first Spam-detecting AI trained entirely in simulation and deployed on a physical robot.
OpenAI Blog · 116mo ago
4 min 
Business
Evolution strategies as a scalable alternative to reinforcement learning
We’ve discovered that evolution strategies (ES), an optimization technique that’s been known for decades, rivals the performance of standard reinforcement learning (RL) techniques on modern RL...
OpenAI Blog · 116mo ago
4 min 
Business
Business
Distill
Support today’s launch of Distill, a new kind of journal aimed at excellent communication of machine learning results (novel or existing).
OpenAI Blog · 116mo ago
4 min 
Business
Learning to communicate
In this post we’ll outline new OpenAI research in which agents develop their own language.
#openai
#agent
OpenAI Blog · 117mo ago
4 min 
Business
Emergence of grounded compositional language in multi-agent populations
Emergence of grounded compositional language in multi-agent populations.
#agent
OpenAI Blog · 117mo ago
4 min 
Business
Prediction and control with temporal segment models
Prediction and control with temporal segment models.
OpenAI Blog · 117mo ago
4 min 
Business
Business
Attacking machine learning with adversarial examples
Adversarial examples are inputs to machine learning models that an attacker has intentionally designed to cause the model to make a mistake; they’re like optical illusions for machines. In this...
OpenAI Blog · 117mo ago
4 min 
Business
Adversarial attacks on neural network policies
Adversarial attacks on neural network policies.
OpenAI Blog · 118mo ago
4 min