dorje

Deep Learning, Knowledge Representation and Reasoning, Robotics.

China

Pinned Repositories

iLQG
Iterative LQG program for nonlinear plants with bounded controls based on the algorithm described in: Todorov, E. and Li, W. (2005) A generalized iterative LQG method for locally-optimal feedback control of constrained nonlinear stochastic systems.
Language:Python0 1 00
maze
using deep reinforcement learning to learn a very simple maze game
Language:Python6 2 02
neural-style
Neural style in TensorFlow! • http://www.anishathalye.com/2015/12/19/an-ai-that-can-mimic-any-artist/ • https://git.io/style
Language:Python0 1 00
Simple-Evolutionary
A very simple example of optimizing a three-unknowns equation.
Language:Jupyter Notebook0 2 00
About-us
Neural Knowledge DNA Lab
0 1 00

dorje/maze
using deep reinforcement learning to learn a very simple maze game
Language:Python6 2 02
dorje/iLQG
Iterative LQG program for nonlinear plants with bounded controls based on the algorithm described in: Todorov, E. and Li, W. (2005) A generalized iterative LQG method for locally-optimal feedback control of constrained nonlinear stochastic systems.
Language:Python0 1 00
dorje/neural-style
Neural style in TensorFlow! • http://www.anishathalye.com/2015/12/19/an-ai-that-can-mimic-any-artist/ • https://git.io/style
Language:Python0 1 00
dorje/Simple-Evolutionary
A very simple example of optimizing a three-unknowns equation.
Language:Jupyter Notebook0 2 00