Hacker News new | ask | show | jobs
user: danijar
created: 2015-04-26
karma: 127

submissions:

DeepMind's Dreamer 4: Training Agents Inside of Scalable World Models
1 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
Mastering diverse control tasks through world models
3 points | 0 comments
0 points | 0 comments
Learning to Walk in the Real World in 1 Hour
1 points | 0 comments
Robot dog just taught itself to walk
11 points | 0 comments
DayDreamer: World Models for Physical Robot Learning
5 points | 0 comments
0 points | 0 comments
0 points | 0 comments
PlaNet: A Deep Planning Network for Reinforcement Learning
42 points | 3 comments
Patterns for Fast Prototyping with TensorFlow
1 points | 0 comments
Reliable Uncertainty Estimates in Neural Networks Using Noise Contrastive Priors
4 points | 0 comments
Why Mean Squared Error?
37 points | 8 comments
Building Variational Auto-Encoders in TensorFlow
3 points | 0 comments
Layer Norm and GRU for State of the Art Language Modeling
13 points | 0 comments
Benchmarking Recurrent Networks for Language Modeling
2 points | 0 comments
Confession of a so-called AI expert
6 points | 0 comments
Tips for Training Recurrent Neural Networks
8 points | 0 comments
0 points | 0 comments
0 points | 0 comments
Show HN: Mindpark - Playing Video Games with Deep Learning in Python
24 points | 2 comments