corpus.blog
41,554 blogs · 4,904,241 posts Claim your blog
Back to OpenAI
Blog · corpus.blog/blogs/openai.com/posts

OpenAI

openai.com

2017

Learning to model other mindsoriginal ↗
14 Sept 2017
Learning with opponent-learning awarenessoriginal ↗
13 Sept 2017
OpenAI Baselines: ACKTR & A2Coriginal ↗
18 Aug 2017
More on Dota 2original ↗
16 Aug 2017
Dota 2original ↗
11 Aug 2017
Gathering human feedbackoriginal ↗
3 Aug 2017
Better exploration with parameter noiseoriginal ↗
27 Jul 2017
Proximal Policy Optimizationoriginal ↗
20 Jul 2017
Robust adversarial inputsoriginal ↗
17 Jul 2017
Hindsight Experience Replayoriginal ↗
5 Jul 2017
Teacher–student curriculum learningoriginal ↗
1 Jul 2017
Faster physics in Pythonoriginal ↗
28 Jun 2017
Learning from human preferencesoriginal ↗
13 Jun 2017
Learning to cooperate, compete, and communicateoriginal ↗
8 Jun 2017
UCB exploration via Q-ensemblesoriginal ↗
5 Jun 2017
OpenAI Baselines: DQNoriginal ↗
24 May 2017
Robots that learnoriginal ↗
16 May 2017
Roboschooloriginal ↗
15 May 2017
Equivalence between policy gradients and soft Q-learningoriginal ↗
21 Apr 2017
Stochastic Neural Networks for hierarchical reinforcement learningoriginal ↗
10 Apr 2017
Unsupervised sentiment neuronoriginal ↗
6 Apr 2017
Spam detection in the physical worldoriginal ↗
1 Apr 2017
Evolution strategies as a scalable alternative to reinforcement learningoriginal ↗
24 Mar 2017
One-shot imitation learningoriginal ↗
21 Mar 2017
Distilloriginal ↗
20 Mar 2017
Learning to communicateoriginal ↗
16 Mar 2017
Emergence of grounded compositional language in multi-agent populationsoriginal ↗
15 Mar 2017
Prediction and control with temporal segment modelsoriginal ↗
12 Mar 2017
Third-person imitation learningoriginal ↗
6 Mar 2017
Attacking machine learning with adversarial examplesoriginal ↗
24 Feb 2017
Adversarial attacks on neural network policiesoriginal ↗
8 Feb 2017
Team updateoriginal ↗
30 Jan 2017
PixelCNN++: Improving the PixelCNN with discretized logistic mixture likelihood and other modificationsoriginal ↗
19 Jan 2017

2016

Faulty reward functions in the wildoriginal ↗
21 Dec 2016
Universeoriginal ↗
5 Dec 2016
#Exploration: A study of count-based exploration for deep reinforcement learningoriginal ↗
15 Nov 2016
OpenAI and Microsoftoriginal ↗
15 Nov 2016
On the quantitative analysis of decoder-based generative modelsoriginal ↗
14 Nov 2016
A connection between generative adversarial networks, inverse reinforcement learning, and energy-based modelsoriginal ↗
11 Nov 2016
RL²: Fast reinforcement learning via slow reinforcement learningoriginal ↗
9 Nov 2016
Variational lossy autoencoderoriginal ↗
8 Nov 2016
Extensions and limitations of the neural GPUoriginal ↗
2 Nov 2016
Semi-supervised knowledge transfer for deep learning from private training dataoriginal ↗
18 Oct 2016
Report from the self-organizing conferenceoriginal ↗
13 Oct 2016
Transfer from simulation to real world through learning deep inverse dynamics modeloriginal ↗
11 Oct 2016
Infrastructure for deep learningoriginal ↗
29 Aug 2016
Machine Learning Unconferenceoriginal ↗
18 Aug 2016
Team updateoriginal ↗
16 Aug 2016
Special projectsoriginal ↗
28 Jul 2016
Concrete AI safety problemsoriginal ↗
21 Jun 2016
OpenAI technical goalsoriginal ↗
20 Jun 2016
Generative modelsoriginal ↗
16 Jun 2016
Team updateoriginal ↗
25 May 2016
Adversarial training methods for semi-supervised text classificationoriginal ↗
25 May 2016
OpenAI Gym Betaoriginal ↗
27 Apr 2016
Welcome, Pieter and Shivon!original ↗
26 Apr 2016
Team++original ↗
31 Mar 2016
Weight normalization: A simple reparameterization to accelerate training of deep neural networksoriginal ↗
25 Feb 2016

2015

Introducing OpenAIoriginal ↗
11 Dec 2015
Previous