MahanFathi/TRPO-TensorFlow

Stars
18
Rank 1,208,065 (Top 24 %)
Language
Python
Created almost 7 years ago
Updated over 6 years ago

MahanFathi/TRPO-TensorFlow

MahanFathi

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Trust Region Policy Optimization (TRPO) in pure TensorFlow

CS231

Complete Assignments for CS231n: Convolutional Neural Networks for Visual Recognition

Jupyter Notebook

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

end2end-self-driving-car

End-to-end Self-driving Car (Behavioral Cloning)

UnsupervisedObjectDetection

Use your classification neural network for object detection and localization

HJxB

Continuous-Time/State/Action Fitted Value Iteration via Hamilton-Jacobi-Bellman (HJB)

OBJET

OBJET: A Computer Vision Graphical Sandbox

Unity2OpenSim

Regenerate Movements of Unity w/ OpenSim

Discrete-Mechanics-and-Optimal-Control

DMOC method for a simple pendulum swing-up control

TrajOpt-KneedWalker

Finding a stable limit cycle for a passive kneed walker using trajectory optimization.

Jupyter Notebook

DeepDPG-TensorFlow

TensorFlow Implementation of Deep Deterministic Policy Gradients for Continuous OpenAI Gym Environments

gail

A Frankenstein implementation of "Generative Adversarial Imitation Learning".

S4RL

Offline RL with S4

DMPx

Dynamic Movement Primitives in JAX

DeepAnaglyph3D

End-to-end generation of good old red-cyan 3D images via CNNs