Search: blog.openai.com | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

1.

OpenAI Five (blog.openai.com)

646 points

8 years ago

2.

Unsupervised sentiment neuron (blog.openai.com)

603 points

9 years ago

3.

Robots that learn (blog.openai.com)

481 points

9 years ago

4.

Learning Dexterity (blog.openai.com)

470 points

8 years ago

5.

Better Language Models and Their Implications (blog.openai.com)

426 points

7 years ago

6.

Competitive Self-Play (blog.openai.com)

374 points

9 years ago

7.

AI and Compute (blog.openai.com)

347 points

8 years ago

8.

Preparing for Malicious Uses of AI (blog.openai.com)

330 points

8 years ago

9.

OpenAI Five Benchmark: Results (blog.openai.com)

281 points

8 years ago

10.

Learning a hierarchy (blog.openai.com)

267 points

9 years ago

11.

Scaling Kubernetes to 2,500 Nodes (blog.openai.com)

265 points

8 years ago

12.

More on Dota 2 (blog.openai.com)

252 points

9 years ago

13.

Roboschool: open-source software for robot simulation (blog.openai.com)

244 points

9 years ago

14.

OpenAI Charter (blog.openai.com)

238 points

8 years ago

15.

OpenAI Baselines (blog.openai.com)

223 points

9 years ago

16.

OpenAI Five Benchmark (blog.openai.com)

209 points

8 years ago

17.

Glow: Better Reversible Generative Models (blog.openai.com)

208 points

8 years ago

18.

Learning to Cooperate, Compete, and Communicate (blog.openai.com)

199 points

9 years ago

19.

Improving Language Understanding with Unsupervised Learning (blog.openai.com)

191 points

8 years ago

20.

How AI Training Scales (blog.openai.com)

176 points

7 years ago

21.

Spinning Up in Deep RL (blog.openai.com)

169 points

8 years ago

22.

Learning Concepts with Energy Functions (blog.openai.com)

166 points

8 years ago

23.

Robust Adversarial Examples (blog.openai.com)

166 points

9 years ago

24.

Reinforcement Learning with Prediction-Based Rewards (blog.openai.com)

165 points

8 years ago

25.

Gym Retro (blog.openai.com)

161 points

8 years ago

26.

Learning ‘Montezuma’s Revenge’ from a single demonstration (blog.openai.com)

151 points

8 years ago

27.

Reptile: A Scalable Meta-Learning Algorithm (blog.openai.com)

140 points

stochastic_monk

8 years ago

28.

Interpretable Machine Learning Through Teaching (blog.openai.com)

134 points

8 years ago

29.

Nonlinear Computation in Deep Linear Networks (blog.openai.com)

128 points

9 years ago

30.

Evolution Strategies as a Scalable Alternative to Reinforcement Learning (blog.openai.com)

118 points

9 years ago