Pinned Repositories
CS231
Complete Assignments for CS231n: Convolutional Neural Networks for Visual Recognition
end2end-self-driving-car
End-to-end Self-driving Car (Behavioral Cloning)
HJxB
Continuous-Time/State/Action Fitted Value Iteration via Hamilton-Jacobi-Bellman (HJB)
iLQG-MuJoCo
Iterative LQG for a couple of MuJoCo models
LQR-RRTstar
LQR-RRT* method is used for random motion planning of a simple pendulum in it's phase plot
Model-Based-RL
Model-based Policy Gradients
OBJET
OBJET: A Computer Vision Graphical Sandbox
TRPO-TensorFlow
Trust Region Policy Optimization (TRPO) in pure TensorFlow
Unity2OpenSim
Regenerate Movements of Unity w/ OpenSim
UnsupervisedObjectDetection
Use your classification neural network for object detection and localization
MahanFathi's Repositories
MahanFathi/CS231
Complete Assignments for CS231n: Convolutional Neural Networks for Visual Recognition
MahanFathi/iLQG-MuJoCo
Iterative LQG for a couple of MuJoCo models
MahanFathi/Model-Based-RL
Model-based Policy Gradients
MahanFathi/end2end-self-driving-car
End-to-end Self-driving Car (Behavioral Cloning)
MahanFathi/UnsupervisedObjectDetection
Use your classification neural network for object detection and localization
MahanFathi/HJxB
Continuous-Time/State/Action Fitted Value Iteration via Hamilton-Jacobi-Bellman (HJB)
MahanFathi/OBJET
OBJET: A Computer Vision Graphical Sandbox
MahanFathi/Unity2OpenSim
Regenerate Movements of Unity w/ OpenSim
MahanFathi/TrajOpt-KneedWalker
Finding a stable limit cycle for a passive kneed walker using trajectory optimization.
MahanFathi/S4RL
Offline RL with S4
MahanFathi/gail
A Frankenstein implementation of "Generative Adversarial Imitation Learning".
MahanFathi/DeepAnaglyph3D
End-to-end generation of good old red-cyan 3D images via CNNs
MahanFathi/DMPx
Dynamic Movement Primitives in JAX
MahanFathi/.files
config files for i3, doom emacs, vim, fish, etc.
MahanFathi/GCxEBM
goal-conditioned energy-based models
MahanFathi/go-rest
simple rest api in go
MahanFathi/ift6163_homeworks
MahanFathi/JEM
Energy-based Option-like Discovery
MahanFathi/junk
all kinda shit here
MahanFathi/LearnOpenGL
recently started to dabble in OpenGL
MahanFathi/length-generalization
Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023
MahanFathi/long-convs
long convolutions in jax
MahanFathi/MahanFathi
MahanFathi/MAYO
Usable Implementation of "Bootstrap Your Own Latent" self-supervised learning, from Deepmind, in Pytorch
MahanFathi/mjDS
MahanFathi/NxDP
MahanFathi/s4
Structured state space sequence models
MahanFathi/specssm
Spectral State-Space Models
MahanFathi/sub-q-learning
break up the Q-function in linear parts which correspond to subrewards
MahanFathi/trabrax
Trajectory Optimization on BRAX